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

Comparing IO-AIO/README (file contents):
Revision 1.43 by root, Sun Jan 10 23:44:02 2010 UTC vs.
Revision 1.60 by root, Tue Jul 31 22:27:49 2018 UTC

1NAME 1NAME
2 IO::AIO - Asynchronous Input/Output 2 IO::AIO - Asynchronous/Advanced Input/Output
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", IO::AIO::O_RDONLY, 0, sub {
8 my $fh = shift 8 my $fh = shift
9 or die "/etc/passwd: $!"; 9 or die "/etc/passwd: $!";
10 ... 10 ...
11 }; 11 };
12 12
… …
55 not well-supported or restricted (GNU/Linux doesn't allow them on normal 55 not well-supported or restricted (GNU/Linux doesn't allow them on normal
56 files currently, for example), and they would only support aio_read and 56 files currently, for example), and they would only support aio_read and
57 aio_write, so the remaining functionality would have to be implemented 57 aio_write, so the remaining functionality would have to be implemented
58 using threads anyway. 58 using threads anyway.
59 59
60 In addition to asynchronous I/O, this module also exports some rather
61 arcane interfaces, such as "madvise" or linux's "splice" system call,
62 which is why the "A" in "AIO" can also mean *advanced*.
63
60 Although the module will work in the presence of other (Perl-) threads, 64 Although the module will work in the presence of other (Perl-) threads,
61 it is currently not reentrant in any way, so use appropriate locking 65 it is currently not reentrant in any way, so use appropriate locking
62 yourself, always call "poll_cb" from within the same thread, or never 66 yourself, always call "poll_cb" from within the same thread, or never
63 call "poll_cb" (or other "aio_" functions) recursively. 67 call "poll_cb" (or other "aio_" functions) recursively.
64 68
65 EXAMPLE 69 EXAMPLE
66 This is a simple example that uses the EV module and loads /etc/passwd 70 This is a simple example that uses the EV module and loads /etc/passwd
67 asynchronously: 71 asynchronously:
68 72
69 use Fcntl;
70 use EV; 73 use EV;
71 use IO::AIO; 74 use IO::AIO;
72 75
73 # register the IO::AIO callback with EV 76 # register the IO::AIO callback with EV
74 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; 77 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
75 78
76 # queue the request to open /etc/passwd 79 # queue the request to open /etc/passwd
77 aio_open "/etc/passwd", O_RDONLY, 0, sub { 80 aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
78 my $fh = shift 81 my $fh = shift
79 or die "error while opening: $!"; 82 or die "error while opening: $!";
80 83
81 # stat'ing filehandles is generally non-blocking 84 # stat'ing filehandles is generally non-blocking
82 my $size = -s $fh; 85 my $size = -s $fh;
… …
91 94
92 # file contents now in $contents 95 # file contents now in $contents
93 print $contents; 96 print $contents;
94 97
95 # exit event loop and program 98 # exit event loop and program
96 EV::unloop; 99 EV::break;
97 }; 100 };
98 }; 101 };
99 102
100 # possibly queue up other requests, or open GUI windows, 103 # possibly queue up other requests, or open GUI windows,
101 # check for sockets etc. etc. 104 # check for sockets etc. etc.
102 105
103 # process events as long as there are some: 106 # process events as long as there are some:
104 EV::loop; 107 EV::run;
105 108
106REQUEST ANATOMY AND LIFETIME 109REQUEST ANATOMY AND LIFETIME
107 Every "aio_*" function creates a request. which is a C data structure 110 Every "aio_*" function creates a request. which is a C data structure
108 not directly visible to Perl. 111 not directly visible to Perl.
109 112
… …
146 the actual aio request is severed and calling its methods will 149 the actual aio request is severed and calling its methods will
147 either do nothing or result in a runtime error). 150 either do nothing or result in a runtime error).
148 151
149FUNCTIONS 152FUNCTIONS
150 QUICK OVERVIEW 153 QUICK OVERVIEW
151 This section simply lists the prototypes of the most important functions 154 This section simply lists the prototypes most of the functions for quick
152 for quick reference. See the following sections for function-by-function 155 reference. See the following sections for function-by-function
153 documentation. 156 documentation.
154 157
158 aio_wd $pathname, $callback->($wd)
155 aio_open $pathname, $flags, $mode, $callback->($fh) 159 aio_open $pathname, $flags, $mode, $callback->($fh)
156 aio_close $fh, $callback->($status) 160 aio_close $fh, $callback->($status)
161 aio_seek $fh,$offset,$whence, $callback->($offs)
157 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 162 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
158 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 163 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
159 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) 164 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
160 aio_readahead $fh,$offset,$length, $callback->($retval) 165 aio_readahead $fh,$offset,$length, $callback->($retval)
161 aio_stat $fh_or_path, $callback->($status) 166 aio_stat $fh_or_path, $callback->($status)
162 aio_lstat $fh, $callback->($status) 167 aio_lstat $fh, $callback->($status)
163 aio_statvfs $fh_or_path, $callback->($statvfs) 168 aio_statvfs $fh_or_path, $callback->($statvfs)
164 aio_utime $fh_or_path, $atime, $mtime, $callback->($status) 169 aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
165 aio_chown $fh_or_path, $uid, $gid, $callback->($status) 170 aio_chown $fh_or_path, $uid, $gid, $callback->($status)
171 aio_chmod $fh_or_path, $mode, $callback->($status)
166 aio_truncate $fh_or_path, $offset, $callback->($status) 172 aio_truncate $fh_or_path, $offset, $callback->($status)
167 aio_chmod $fh_or_path, $mode, $callback->($status) 173 aio_allocate $fh, $mode, $offset, $len, $callback->($status)
174 aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
168 aio_unlink $pathname, $callback->($status) 175 aio_unlink $pathname, $callback->($status)
169 aio_mknod $path, $mode, $dev, $callback->($status) 176 aio_mknod $pathname, $mode, $dev, $callback->($status)
170 aio_link $srcpath, $dstpath, $callback->($status) 177 aio_link $srcpath, $dstpath, $callback->($status)
171 aio_symlink $srcpath, $dstpath, $callback->($status) 178 aio_symlink $srcpath, $dstpath, $callback->($status)
172 aio_readlink $path, $callback->($link) 179 aio_readlink $pathname, $callback->($link)
180 aio_realpath $pathname, $callback->($path)
173 aio_rename $srcpath, $dstpath, $callback->($status) 181 aio_rename $srcpath, $dstpath, $callback->($status)
182 aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
174 aio_mkdir $pathname, $mode, $callback->($status) 183 aio_mkdir $pathname, $mode, $callback->($status)
175 aio_rmdir $pathname, $callback->($status) 184 aio_rmdir $pathname, $callback->($status)
176 aio_readdir $pathname, $callback->($entries) 185 aio_readdir $pathname, $callback->($entries)
177 aio_readdirx $pathname, $flags, $callback->($entries, $flags) 186 aio_readdirx $pathname, $flags, $callback->($entries, $flags)
178 IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST 187 IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
179 IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN 188 IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
189 aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
180 aio_load $path, $data, $callback->($status) 190 aio_load $pathname, $data, $callback->($status)
181 aio_copy $srcpath, $dstpath, $callback->($status) 191 aio_copy $srcpath, $dstpath, $callback->($status)
182 aio_move $srcpath, $dstpath, $callback->($status) 192 aio_move $srcpath, $dstpath, $callback->($status)
183 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
184 aio_rmtree $path, $callback->($status) 193 aio_rmtree $pathname, $callback->($status)
194 aio_fcntl $fh, $cmd, $arg, $callback->($status)
195 aio_ioctl $fh, $request, $buf, $callback->($status)
185 aio_sync $callback->($status) 196 aio_sync $callback->($status)
197 aio_syncfs $fh, $callback->($status)
186 aio_fsync $fh, $callback->($status) 198 aio_fsync $fh, $callback->($status)
187 aio_fdatasync $fh, $callback->($status) 199 aio_fdatasync $fh, $callback->($status)
188 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) 200 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
189 aio_pathsync $path, $callback->($status) 201 aio_pathsync $pathname, $callback->($status)
190 aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) 202 aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
191 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) 203 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
204 aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
205 aio_mlockall $flags, $callback->($status)
192 aio_group $callback->(...) 206 aio_group $callback->(...)
193 aio_nop $callback->() 207 aio_nop $callback->()
194 208
195 $prev_pri = aioreq_pri [$pri] 209 $prev_pri = aioreq_pri [$pri]
196 aioreq_nice $pri_adjust 210 aioreq_nice $pri_adjust
… …
202 IO::AIO::max_poll_reqs $nreqs 216 IO::AIO::max_poll_reqs $nreqs
203 IO::AIO::max_poll_time $seconds 217 IO::AIO::max_poll_time $seconds
204 IO::AIO::min_parallel $nthreads 218 IO::AIO::min_parallel $nthreads
205 IO::AIO::max_parallel $nthreads 219 IO::AIO::max_parallel $nthreads
206 IO::AIO::max_idle $nthreads 220 IO::AIO::max_idle $nthreads
221 IO::AIO::idle_timeout $seconds
207 IO::AIO::max_outstanding $maxreqs 222 IO::AIO::max_outstanding $maxreqs
208 IO::AIO::nreqs 223 IO::AIO::nreqs
209 IO::AIO::nready 224 IO::AIO::nready
210 IO::AIO::npending 225 IO::AIO::npending
226 $nfd = IO::AIO::get_fdlimit [EXPERIMENTAL]
227 IO::AIO::min_fdlimit $nfd [EXPERIMENTAL]
211 228
212 IO::AIO::sendfile $ofh, $ifh, $offset, $count 229 IO::AIO::sendfile $ofh, $ifh, $offset, $count
213 IO::AIO::fadvise $fh, $offset, $len, $advice 230 IO::AIO::fadvise $fh, $offset, $len, $advice
214 IO::AIO::mlockall $flags 231 IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
232 IO::AIO::munmap $scalar
233 IO::AIO::mremap $scalar, $new_length, $flags[, $new_address]
234 IO::AIO::madvise $scalar, $offset, $length, $advice
235 IO::AIO::mprotect $scalar, $offset, $length, $protect
236 IO::AIO::munlock $scalar, $offset = 0, $length = undef
215 IO::AIO::munlockall 237 IO::AIO::munlockall
216 238
217 AIO REQUEST FUNCTIONS 239 API NOTES
218 All the "aio_*" calls are more or less thin wrappers around the syscall 240 All the "aio_*" calls are more or less thin wrappers around the syscall
219 with the same name (sans "aio_"). The arguments are similar or 241 with the same name (sans "aio_"). The arguments are similar or
220 identical, and they all accept an additional (and optional) $callback 242 identical, and they all accept an additional (and optional) $callback
221 argument which must be a code reference. This code reference will get 243 argument which must be a code reference. This code reference will be
222 called with the syscall return code (e.g. most syscalls return -1 on
223 error, unlike perl, which usually delivers "false") as its sole argument
224 after the given syscall has been executed asynchronously. 244 called after the syscall has been executed in an asynchronous fashion.
245 The results of the request will be passed as arguments to the callback
246 (and, if an error occured, in $!) - for most requests the syscall return
247 code (e.g. most syscalls return -1 on error, unlike perl, which usually
248 delivers "false").
249
250 Some requests (such as "aio_readdir") pass the actual results and
251 communicate failures by passing "undef".
225 252
226 All functions expecting a filehandle keep a copy of the filehandle 253 All functions expecting a filehandle keep a copy of the filehandle
227 internally until the request has finished. 254 internally until the request has finished.
228 255
229 All functions return request objects of type IO::AIO::REQ that allow 256 All functions return request objects of type IO::AIO::REQ that allow
230 further manipulation of those requests while they are in-flight. 257 further manipulation of those requests while they are in-flight.
231 258
232 The pathnames you pass to these routines *must* be absolute and encoded 259 The pathnames you pass to these routines *should* be absolute. The
233 as octets. The reason for the former is that at the time the request is 260 reason for this is that at the time the request is being executed, the
234 being executed, the current working directory could have changed. 261 current working directory could have changed. Alternatively, you can
235 Alternatively, you can make sure that you never change the current 262 make sure that you never change the current working directory anywhere
236 working directory anywhere in the program and then use relative paths. 263 in the program and then use relative paths. You can also take advantage
264 of IO::AIOs working directory abstraction, that lets you specify paths
265 relative to some previously-opened "working directory object" - see the
266 description of the "IO::AIO::WD" class later in this document.
237 267
238 To encode pathnames as octets, either make sure you either: a) always 268 To encode pathnames as octets, either make sure you either: a) always
239 pass in filenames you got from outside (command line, readdir etc.) 269 pass in filenames you got from outside (command line, readdir etc.)
240 without tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module 270 without tinkering, b) are in your native filesystem encoding, c) use the
241 and encode your pathnames to the locale (or other) encoding in effect in 271 Encode module and encode your pathnames to the locale (or other)
242 the user environment, d) use Glib::filename_from_unicode on unicode 272 encoding in effect in the user environment, d) use
243 filenames or e) use something else to ensure your scalar has the correct 273 Glib::filename_from_unicode on unicode filenames or e) use something
244 contents. 274 else to ensure your scalar has the correct contents.
245 275
246 This works, btw. independent of the internal UTF-8 bit, which IO::AIO 276 This works, btw. independent of the internal UTF-8 bit, which IO::AIO
247 handles correctly whether it is set or not. 277 handles correctly whether it is set or not.
248 278
279 AIO REQUEST FUNCTIONS
249 $prev_pri = aioreq_pri [$pri] 280 $prev_pri = aioreq_pri [$pri]
250 Returns the priority value that would be used for the next request 281 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. 282 and, if $pri is given, sets the priority for the next aio request.
252 283
253 The default priority is 0, the minimum and maximum priorities are -4 284 The default priority is 0, the minimum and maximum priorities are -4
… …
275 Similar to "aioreq_pri", but subtracts the given value from the 306 Similar to "aioreq_pri", but subtracts the given value from the
276 current priority, so the effect is cumulative. 307 current priority, so the effect is cumulative.
277 308
278 aio_open $pathname, $flags, $mode, $callback->($fh) 309 aio_open $pathname, $flags, $mode, $callback->($fh)
279 Asynchronously open or create a file and call the callback with a 310 Asynchronously open or create a file and call the callback with a
280 newly created filehandle for the file. 311 newly created filehandle for the file (or "undef" in case of an
312 error).
281 313
282 The pathname passed to "aio_open" must be absolute. See API NOTES, 314 The pathname passed to "aio_open" must be absolute. See API NOTES,
283 above, for an explanation. 315 above, for an explanation.
284 316
285 The $flags argument is a bitmask. See the "Fcntl" module for a list. 317 The $flags argument is a bitmask. See the "Fcntl" module for a list.
… …
292 will be modified by the umask in effect then the request is being 324 will be modified by the umask in effect then the request is being
293 executed, so better never change the umask. 325 executed, so better never change the umask.
294 326
295 Example: 327 Example:
296 328
297 aio_open "/etc/passwd", O_RDONLY, 0, sub { 329 aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
298 if ($_[0]) { 330 if ($_[0]) {
299 print "open successful, fh is $_[0]\n"; 331 print "open successful, fh is $_[0]\n";
300 ... 332 ...
301 } else { 333 } else {
302 die "open failed: $!\n"; 334 die "open failed: $!\n";
303 } 335 }
304 }; 336 };
305 337
338 In addition to all the common open modes/flags ("O_RDONLY",
339 "O_WRONLY", "O_RDWR", "O_CREAT", "O_TRUNC", "O_EXCL" and
340 "O_APPEND"), the following POSIX and non-POSIX constants are
341 available (missing ones on your system are, as usual, 0):
342
343 "O_ASYNC", "O_DIRECT", "O_NOATIME", "O_CLOEXEC", "O_NOCTTY",
344 "O_NOFOLLOW", "O_NONBLOCK", "O_EXEC", "O_SEARCH", "O_DIRECTORY",
345 "O_DSYNC", "O_RSYNC", "O_SYNC", "O_PATH", "O_TMPFILE", "O_TTY_INIT"
346 and "O_ACCMODE".
347
306 aio_close $fh, $callback->($status) 348 aio_close $fh, $callback->($status)
307 Asynchronously close a file and call the callback with the result 349 Asynchronously close a file and call the callback with the result
308 code. 350 code.
309 351
310 Unfortunately, you can't do this to perl. Perl *insists* very 352 Unfortunately, you can't do this to perl. Perl *insists* very
… …
315 will use dup2 to overwrite the file descriptor with the write-end of 357 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). 358 a pipe (the pipe fd will be created on demand and will be cached).
317 359
318 Or in other words: the file descriptor will be closed, but it will 360 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. 361 not be free for reuse until the perl filehandle is closed.
362
363 aio_seek $fh, $offset, $whence, $callback->($offs)
364 Seeks the filehandle to the new $offset, similarly to perl's
365 "sysseek". The $whence can use the traditional values (0 for
366 "IO::AIO::SEEK_SET", 1 for "IO::AIO::SEEK_CUR" or 2 for
367 "IO::AIO::SEEK_END").
368
369 The resulting absolute offset will be passed to the callback, or -1
370 in case of an error.
371
372 In theory, the $whence constants could be different than the
373 corresponding values from Fcntl, but perl guarantees they are the
374 same, so don't panic.
375
376 As a GNU/Linux (and maybe Solaris) extension, also the constants
377 "IO::AIO::SEEK_DATA" and "IO::AIO::SEEK_HOLE" are available, if they
378 could be found. No guarantees about suitability for use in
379 "aio_seek" or Perl's "sysseek" can be made though, although I would
380 naively assume they "just work".
320 381
321 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 382 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
322 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 383 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
323 Reads or writes $length bytes from or to the specified $fh and 384 Reads or writes $length bytes from or to the specified $fh and
324 $offset into the scalar given by $data and offset $dataoffset and 385 $offset into the scalar given by $data and offset $dataoffset and
325 calls the callback without the actual number of bytes read (or -1 on 386 calls the callback with the actual number of bytes transferred (or
326 error, just like the syscall). 387 -1 on error, just like the syscall).
327 388
328 "aio_read" will, like "sysread", shrink or grow the $data scalar to 389 "aio_read" will, like "sysread", shrink or grow the $data scalar to
329 offset plus the actual number of bytes read. 390 offset plus the actual number of bytes read.
330 391
331 If $offset is undefined, then the current file descriptor offset 392 If $offset is undefined, then the current file descriptor offset
… …
353 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) 414 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
354 Tries to copy $length bytes from $in_fh to $out_fh. It starts 415 Tries to copy $length bytes from $in_fh to $out_fh. It starts
355 reading at byte offset $in_offset, and starts writing at the current 416 reading at byte offset $in_offset, and starts writing at the current
356 file offset of $out_fh. Because of that, it is not safe to issue 417 file offset of $out_fh. Because of that, it is not safe to issue
357 more than one "aio_sendfile" per $out_fh, as they will interfere 418 more than one "aio_sendfile" per $out_fh, as they will interfere
358 with each other. 419 with each other. The same $in_fh works fine though, as this function
420 does not move or use the file offset of $in_fh.
359 421
422 Please note that "aio_sendfile" can read more bytes from $in_fh than
423 are written, and there is no way to find out how many more bytes
424 have been read from "aio_sendfile" alone, as "aio_sendfile" only
425 provides the number of bytes written to $out_fh. Only if the result
426 value equals $length one can assume that $length bytes have been
427 read.
428
429 Unlike with other "aio_" functions, it makes a lot of sense to use
430 "aio_sendfile" on non-blocking sockets, as long as one end
431 (typically the $in_fh) is a file - the file I/O will then be
432 asynchronous, while the socket I/O will be non-blocking. Note,
433 however, that you can run into a trap where "aio_sendfile" reads
434 some data with readahead, then fails to write all data, and when the
435 socket is ready the next time, the data in the cache is already
436 lost, forcing "aio_sendfile" to again hit the disk. Explicit
437 "aio_read" + "aio_write" let's you better control resource usage.
438
360 This call tries to make use of a native "sendfile" syscall to 439 This call tries to make use of a native "sendfile"-like syscall to
361 provide zero-copy operation. For this to work, $out_fh should refer 440 provide zero-copy operation. For this to work, $out_fh should refer
362 to a socket, and $in_fh should refer to an mmap'able file. 441 to a socket, and $in_fh should refer to an mmap'able file.
363 442
364 If a native sendfile cannot be found or it fails with "ENOSYS", 443 If a native sendfile cannot be found or it fails with "ENOSYS",
365 "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK", 444 "EINVAL", "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or
366 it will be emulated, so you can call "aio_sendfile" on any type of 445 "ENOTSOCK", it will be emulated, so you can call "aio_sendfile" on
367 filehandle regardless of the limitations of the operating system. 446 any type of filehandle regardless of the limitations of the
447 operating system.
368 448
369 Please note, however, that "aio_sendfile" can read more bytes from 449 As native sendfile syscalls (as practically any non-POSIX interface
370 $in_fh than are written, and there is no way to find out how many 450 hacked together in a hurry to improve benchmark numbers) tend to be
371 bytes have been read from "aio_sendfile" alone, as "aio_sendfile" 451 rather buggy on many systems, this implementation tries to work
372 only provides the number of bytes written to $out_fh. Only if the 452 around some known bugs in Linux and FreeBSD kernels (probably
373 result value equals $length one can assume that $length bytes have 453 others, too), but that might fail, so you really really should check
374 been read. 454 the return value of "aio_sendfile" - fewer bytes than expected might
455 have been transferred.
375 456
376 aio_readahead $fh,$offset,$length, $callback->($retval) 457 aio_readahead $fh,$offset,$length, $callback->($retval)
377 "aio_readahead" populates the page cache with data from a file so 458 "aio_readahead" populates the page cache with data from a file so
378 that subsequent reads from that file will not block on disk I/O. The 459 that subsequent reads from that file will not block on disk I/O. The
379 $offset argument specifies the starting point from which data is to 460 $offset argument specifies the starting point from which data is to
… …
382 to a page boundary and bytes are read up to the next page boundary 463 to a page boundary and bytes are read up to the next page boundary
383 greater than or equal to (off-set+length). "aio_readahead" does not 464 greater than or equal to (off-set+length). "aio_readahead" does not
384 read beyond the end of the file. The current file offset of the file 465 read beyond the end of the file. The current file offset of the file
385 is left unchanged. 466 is left unchanged.
386 467
387 If that syscall doesn't exist (likely if your OS isn't Linux) it 468 If that syscall doesn't exist (likely if your kernel isn't Linux) it
388 will be emulated by simply reading the data, which would have a 469 will be emulated by simply reading the data, which would have a
389 similar effect. 470 similar effect.
390 471
391 aio_stat $fh_or_path, $callback->($status) 472 aio_stat $fh_or_path, $callback->($status)
392 aio_lstat $fh, $callback->($status) 473 aio_lstat $fh, $callback->($status)
… …
399 480
400 Currently, the stats are always 64-bit-stats, i.e. instead of 481 Currently, the stats are always 64-bit-stats, i.e. instead of
401 returning an error when stat'ing a large file, the results will be 482 returning an error when stat'ing a large file, the results will be
402 silently truncated unless perl itself is compiled with large file 483 silently truncated unless perl itself is compiled with large file
403 support. 484 support.
485
486 To help interpret the mode and dev/rdev stat values, IO::AIO offers
487 the following constants and functions (if not implemented, the
488 constants will be 0 and the functions will either "croak" or fall
489 back on traditional behaviour).
490
491 "S_IFMT", "S_IFIFO", "S_IFCHR", "S_IFBLK", "S_IFLNK", "S_IFREG",
492 "S_IFDIR", "S_IFWHT", "S_IFSOCK", "IO::AIO::major $dev_t",
493 "IO::AIO::minor $dev_t", "IO::AIO::makedev $major, $minor".
404 494
405 Example: Print the length of /etc/passwd: 495 Example: Print the length of /etc/passwd:
406 496
407 aio_stat "/etc/passwd", sub { 497 aio_stat "/etc/passwd", sub {
408 $_[0] and die "stat failed: $!"; 498 $_[0] and die "stat failed: $!";
… …
481 aio_chown "path", 0, undef; 571 aio_chown "path", 0, undef;
482 572
483 aio_truncate $fh_or_path, $offset, $callback->($status) 573 aio_truncate $fh_or_path, $offset, $callback->($status)
484 Works like truncate(2) or ftruncate(2). 574 Works like truncate(2) or ftruncate(2).
485 575
576 aio_allocate $fh, $mode, $offset, $len, $callback->($status)
577 Allocates or frees disk space according to the $mode argument. See
578 the linux "fallocate" documentation for details.
579
580 $mode is usually 0 or "IO::AIO::FALLOC_FL_KEEP_SIZE" to allocate
581 space, or "IO::AIO::FALLOC_FL_PUNCH_HOLE |
582 IO::AIO::FALLOC_FL_KEEP_SIZE", to deallocate a file range.
583
584 IO::AIO also supports "FALLOC_FL_COLLAPSE_RANGE", to remove a range
585 (without leaving a hole), "FALLOC_FL_ZERO_RANGE", to zero a range,
586 "FALLOC_FL_INSERT_RANGE" to insert a range and
587 "FALLOC_FL_UNSHARE_RANGE" to unshare shared blocks (see your
588 fallocate(2) manpage).
589
590 The file system block size used by "fallocate" is presumably the
591 "f_bsize" returned by "statvfs", but different filesystems and
592 filetypes can dictate other limitations.
593
594 If "fallocate" isn't available or cannot be emulated (currently no
595 emulation will be attempted), passes -1 and sets $! to "ENOSYS".
596
486 aio_chmod $fh_or_path, $mode, $callback->($status) 597 aio_chmod $fh_or_path, $mode, $callback->($status)
487 Works like perl's "chmod" function. 598 Works like perl's "chmod" function.
488 599
489 aio_unlink $pathname, $callback->($status) 600 aio_unlink $pathname, $callback->($status)
490 Asynchronously unlink (delete) a file and call the callback with the 601 Asynchronously unlink (delete) a file and call the callback with the
491 result code. 602 result code.
492 603
493 aio_mknod $path, $mode, $dev, $callback->($status) 604 aio_mknod $pathname, $mode, $dev, $callback->($status)
494 [EXPERIMENTAL] 605 [EXPERIMENTAL]
495 606
496 Asynchronously create a device node (or fifo). See mknod(2). 607 Asynchronously create a device node (or fifo). See mknod(2).
497 608
498 The only (POSIX-) portable way of calling this function is: 609 The only (POSIX-) portable way of calling this function is:
499 610
500 aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... 611 aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
612
613 See "aio_stat" for info about some potentially helpful extra
614 constants and functions.
501 615
502 aio_link $srcpath, $dstpath, $callback->($status) 616 aio_link $srcpath, $dstpath, $callback->($status)
503 Asynchronously create a new link to the existing object at $srcpath 617 Asynchronously create a new link to the existing object at $srcpath
504 at the path $dstpath and call the callback with the result code. 618 at the path $dstpath and call the callback with the result code.
505 619
506 aio_symlink $srcpath, $dstpath, $callback->($status) 620 aio_symlink $srcpath, $dstpath, $callback->($status)
507 Asynchronously create a new symbolic link to the existing object at 621 Asynchronously create a new symbolic link to the existing object at
508 $srcpath at the path $dstpath and call the callback with the result 622 $srcpath at the path $dstpath and call the callback with the result
509 code. 623 code.
510 624
511 aio_readlink $path, $callback->($link) 625 aio_readlink $pathname, $callback->($link)
512 Asynchronously read the symlink specified by $path and pass it to 626 Asynchronously read the symlink specified by $path and pass it to
513 the callback. If an error occurs, nothing or undef gets passed to 627 the callback. If an error occurs, nothing or undef gets passed to
514 the callback. 628 the callback.
515 629
630 aio_realpath $pathname, $callback->($path)
631 Asynchronously make the path absolute and resolve any symlinks in
632 $path. The resulting path only consists of directories (same as
633 Cwd::realpath).
634
635 This request can be used to get the absolute path of the current
636 working directory by passing it a path of . (a single dot).
637
516 aio_rename $srcpath, $dstpath, $callback->($status) 638 aio_rename $srcpath, $dstpath, $callback->($status)
517 Asynchronously rename the object at $srcpath to $dstpath, just as 639 Asynchronously rename the object at $srcpath to $dstpath, just as
518 rename(2) and call the callback with the result code. 640 rename(2) and call the callback with the result code.
641
642 On systems that support the AIO::WD working directory abstraction
643 natively, the case "[$wd, "."]" as $srcpath is specialcased -
644 instead of failing, "rename" is called on the absolute path of $wd.
645
646 aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
647 Basically a version of "aio_rename" with an additional $flags
648 argument. Calling this with "$flags=0" is the same as calling
649 "aio_rename".
650
651 Non-zero flags are currently only supported on GNU/Linux systems
652 that support renameat2. Other systems fail with "ENOSYS" in this
653 case.
654
655 The following constants are available (missing ones are, as usual
656 0), see renameat2(2) for details:
657
658 "IO::AIO::RENAME_NOREPLACE", "IO::AIO::RENAME_EXCHANGE" and
659 "IO::AIO::RENAME_WHITEOUT".
519 660
520 aio_mkdir $pathname, $mode, $callback->($status) 661 aio_mkdir $pathname, $mode, $callback->($status)
521 Asynchronously mkdir (create) a directory and call the callback with 662 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 663 the result code. $mode will be modified by the umask at the time the
523 request is executed, so do not change your umask. 664 request is executed, so do not change your umask.
524 665
525 aio_rmdir $pathname, $callback->($status) 666 aio_rmdir $pathname, $callback->($status)
526 Asynchronously rmdir (delete) a directory and call the callback with 667 Asynchronously rmdir (delete) a directory and call the callback with
527 the result code. 668 the result code.
528 669
670 On systems that support the AIO::WD working directory abstraction
671 natively, the case "[$wd, "."]" is specialcased - instead of
672 failing, "rmdir" is called on the absolute path of $wd.
673
529 aio_readdir $pathname, $callback->($entries) 674 aio_readdir $pathname, $callback->($entries)
530 Unlike the POSIX call of the same name, "aio_readdir" reads an 675 Unlike the POSIX call of the same name, "aio_readdir" reads an
531 entire directory (i.e. opendir + readdir + closedir). The entries 676 entire directory (i.e. opendir + readdir + closedir). The entries
532 will not be sorted, and will NOT include the "." and ".." entries. 677 will not be sorted, and will NOT include the "." and ".." entries.
533 678
534 The callback is passed a single argument which is either "undef" or 679 The callback is passed a single argument which is either "undef" or
535 an array-ref with the filenames. 680 an array-ref with the filenames.
536 681
537 aio_readdirx $pathname, $flags, $callback->($entries, $flags) 682 aio_readdirx $pathname, $flags, $callback->($entries, $flags)
538 Quite similar to "aio_readdir", but the $flags argument allows to 683 Quite similar to "aio_readdir", but the $flags argument allows one
539 tune behaviour and output format. In case of an error, $entries will 684 to tune behaviour and output format. In case of an error, $entries
540 be "undef". 685 will be "undef".
541 686
542 The flags are a combination of the following constants, ORed 687 The flags are a combination of the following constants, ORed
543 together (the flags will also be passed to the callback, possibly 688 together (the flags will also be passed to the callback, possibly
544 modified): 689 modified):
545 690
546 IO::AIO::READDIR_DENTS 691 IO::AIO::READDIR_DENTS
547 When this flag is off, then the callback gets an arrayref with 692 Normally the callback gets an arrayref consisting of names only
548 of names only (as with "aio_readdir"), otherwise it gets an 693 (as with "aio_readdir"). If this flag is set, then the callback
549 arrayref with "[$name, $type, $inode]" arrayrefs, each 694 gets an arrayref with "[$name, $type, $inode]" arrayrefs, each
550 describing a single directory entry in more detail. 695 describing a single directory entry in more detail:
551 696
552 $name is the name of the entry. 697 $name is the name of the entry.
553 698
554 $type is one of the "IO::AIO::DT_xxx" constants: 699 $type is one of the "IO::AIO::DT_xxx" constants:
555 700
556 "IO::AIO::DT_UNKNOWN", "IO::AIO::DT_FIFO", "IO::AIO::DT_CHR", 701 "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", 702 "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". 703 "IO::AIO::DT_LNK", "IO::AIO::DT_SOCK", "IO::AIO::DT_WHT".
559 704
560 "IO::AIO::DT_UNKNOWN" means just that: readdir does not know. If 705 "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 706 you need to know, you have to run stat yourself. Also, for
562 reasons, the $type scalars are read-only: you can not modify 707 speed/memory reasons, the $type scalars are read-only: you must
563 them. 708 not modify them.
564 709
565 $inode is the inode number (which might not be exact on systems 710 $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 711 with 64 bit inode numbers and 32 bit perls). This field has
567 unspecified content on systems that do not deliver the inode 712 unspecified content on systems that do not deliver the inode
568 information. 713 information.
569 714
570 IO::AIO::READDIR_DIRS_FIRST 715 IO::AIO::READDIR_DIRS_FIRST
571 When this flag is set, then the names will be returned in an 716 When this flag is set, then the names will be returned in an
572 order where likely directories come first. This is useful when 717 order where likely directories come first, in optimal stat
573 you need to quickly find directories, or you want to find all 718 order. This is useful when you need to quickly find directories,
574 directories while avoiding to stat() each entry. 719 or you want to find all directories while avoiding to stat()
720 each entry.
575 721
576 If the system returns type information in readdir, then this is 722 If the system returns type information in readdir, then this is
577 used to find directories directly. Otherwise, likely directories 723 used to find directories directly. Otherwise, likely directories
578 are files beginning with ".", or otherwise files with no dots, 724 are names beginning with ".", or otherwise names with no dots,
579 of which files with short names are tried first. 725 of which names with short names are tried first.
580 726
581 IO::AIO::READDIR_STAT_ORDER 727 IO::AIO::READDIR_STAT_ORDER
582 When this flag is set, then the names will be returned in an 728 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 729 order suitable for stat()'ing each one. That is, when you plan
584 to stat() all files in the given directory, then the returned 730 to stat() most or all files in the given directory, then the
585 order will likely be fastest. 731 returned order will likely be faster.
586 732
587 If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are 733 If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are
588 specified, then the likely dirs come first, resulting in a less 734 specified, then the likely dirs come first, resulting in a less
589 optimal stat order. 735 optimal stat order for stat'ing all entries, but likely a more
736 optimal order for finding subdirectories.
590 737
591 IO::AIO::READDIR_FOUND_UNKNOWN 738 IO::AIO::READDIR_FOUND_UNKNOWN
592 This flag should not be set when calling "aio_readdirx". 739 This flag should not be set when calling "aio_readdirx".
593 Instead, it is being set by "aio_readdirx", when any of the 740 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 741 $type's found were "IO::AIO::DT_UNKNOWN". The absence of this
595 flag therefore indicates that all $type's are known, which can 742 flag therefore indicates that all $type's are known, which can
596 be used to speed up some algorithms. 743 be used to speed up some algorithms.
597 744
745 aio_slurp $pathname, $offset, $length, $data, $callback->($status)
746 Opens, reads and closes the given file. The data is put into $data,
747 which is resized as required.
748
749 If $offset is negative, then it is counted from the end of the file.
750
751 If $length is zero, then the remaining length of the file is used.
752 Also, in this case, the same limitations to modifying $data apply as
753 when IO::AIO::mmap is used, i.e. it must only be modified in-place
754 with "substr". If the size of the file is known, specifying a
755 non-zero $length results in a performance advantage.
756
757 This request is similar to the older "aio_load" request, but since
758 it is a single request, it might be more efficient to use.
759
760 Example: load /etc/passwd into $passwd.
761
762 my $passwd;
763 aio_slurp "/etc/passwd", 0, 0, $passwd, sub {
764 $_[0] >= 0
765 or die "/etc/passwd: $!\n";
766
767 printf "/etc/passwd is %d bytes long, and contains:\n", length $passwd;
768 print $passwd;
769 };
770 IO::AIO::flush;
771
598 aio_load $path, $data, $callback->($status) 772 aio_load $pathname, $data, $callback->($status)
599 This is a composite request that tries to fully load the given file 773 This is a composite request that tries to fully load the given file
600 into memory. Status is the same as with aio_read. 774 into memory. Status is the same as with aio_read.
775
776 Using "aio_slurp" might be more efficient, as it is a single
777 request.
601 778
602 aio_copy $srcpath, $dstpath, $callback->($status) 779 aio_copy $srcpath, $dstpath, $callback->($status)
603 Try to copy the *file* (directories not supported as either source 780 Try to copy the *file* (directories not supported as either source
604 or destination) from $srcpath to $dstpath and call the callback with 781 or destination) from $srcpath to $dstpath and call the callback with
605 a status of 0 (ok) or -1 (error, see $!). 782 a status of 0 (ok) or -1 (error, see $!).
606 783
784 Existing destination files will be truncated.
785
607 This is a composite request that creates the destination file with 786 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 787 mode 0200 and copies the contents of the source file into it using
609 "aio_sendfile", followed by restoring atime, mtime, access mode and 788 "aio_sendfile", followed by restoring atime, mtime, access mode and
610 uid/gid, in that order. 789 uid/gid, in that order.
611 790
… …
620 799
621 This is a composite request that tries to rename(2) the file first; 800 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" 801 if rename fails with "EXDEV", it copies the file with "aio_copy"
623 and, if that is successful, unlinks the $srcpath. 802 and, if that is successful, unlinks the $srcpath.
624 803
625 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) 804 aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
626 Scans a directory (similar to "aio_readdir") but additionally tries 805 Scans a directory (similar to "aio_readdir") but additionally tries
627 to efficiently separate the entries of directory $path into two sets 806 to efficiently separate the entries of directory $path into two sets
628 of names, directories you can recurse into (directories), and ones 807 of names, directories you can recurse into (directories), and ones
629 you cannot recurse into (everything else, including symlinks to 808 you cannot recurse into (everything else, including symlinks to
630 directories). 809 directories).
631 810
632 "aio_scandir" is a composite request that creates of many sub 811 "aio_scandir" is a composite request that generates many sub
633 requests_ $maxreq specifies the maximum number of outstanding aio 812 requests. $maxreq specifies the maximum number of outstanding aio
634 requests that this function generates. If it is "<= 0", then a 813 requests that this function generates. If it is "<= 0", then a
635 suitable default will be chosen (currently 4). 814 suitable default will be chosen (currently 4).
636 815
637 On error, the callback is called without arguments, otherwise it 816 On error, the callback is called without arguments, otherwise it
638 receives two array-refs with path-relative entry names. 817 receives two array-refs with path-relative entry names.
… …
663 Then entries will be sorted into likely directories a non-initial 842 Then entries will be sorted into likely directories a non-initial
664 dot currently) and likely non-directories (see "aio_readdirx"). Then 843 dot currently) and likely non-directories (see "aio_readdirx"). Then
665 every entry plus an appended "/." will be "stat"'ed, likely 844 every entry plus an appended "/." will be "stat"'ed, likely
666 directories first, in order of their inode numbers. If that 845 directories first, in order of their inode numbers. If that
667 succeeds, it assumes that the entry is a directory or a symlink to 846 succeeds, it assumes that the entry is a directory or a symlink to
668 directory (which will be checked seperately). This is often faster 847 directory (which will be checked separately). This is often faster
669 than stat'ing the entry itself because filesystems might detect the 848 than stat'ing the entry itself because filesystems might detect the
670 type of the entry without reading the inode data (e.g. ext2fs 849 type of the entry without reading the inode data (e.g. ext2fs
671 filetype feature), even on systems that cannot return the filetype 850 filetype feature), even on systems that cannot return the filetype
672 information on readdir. 851 information on readdir.
673 852
… …
679 858
680 It will also likely work on non-POSIX filesystems with reduced 859 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 860 efficiency as those tend to return 0 or 1 as link counts, which
682 disables the directory counting heuristic. 861 disables the directory counting heuristic.
683 862
684 aio_rmtree $path, $callback->($status) 863 aio_rmtree $pathname, $callback->($status)
685 Delete a directory tree starting (and including) $path, return the 864 Delete a directory tree starting (and including) $path, return the
686 status of the final "rmdir" only. This is a composite request that 865 status of the final "rmdir" only. This is a composite request that
687 uses "aio_scandir" to recurse into and rmdir directories, and unlink 866 uses "aio_scandir" to recurse into and rmdir directories, and unlink
688 everything else. 867 everything else.
689 868
869 aio_fcntl $fh, $cmd, $arg, $callback->($status)
870 aio_ioctl $fh, $request, $buf, $callback->($status)
871 These work just like the "fcntl" and "ioctl" built-in functions,
872 except they execute asynchronously and pass the return value to the
873 callback.
874
875 Both calls can be used for a lot of things, some of which make more
876 sense to run asynchronously in their own thread, while some others
877 make less sense. For example, calls that block waiting for external
878 events, such as locking, will also lock down an I/O thread while it
879 is waiting, which can deadlock the whole I/O system. At the same
880 time, there might be no alternative to using a thread to wait.
881
882 So in general, you should only use these calls for things that do
883 (filesystem) I/O, not for things that wait for other events
884 (network, other processes), although if you are careful and know
885 what you are doing, you still can.
886
887 The following constants are available (missing ones are, as usual
888 0):
889
890 "F_DUPFD_CLOEXEC",
891
892 "F_OFD_GETLK", "F_OFD_SETLK", "F_OFD_GETLKW",
893
894 "FIFREEZE", "FITHAW", "FITRIM", "FICLONE", "FICLONERANGE",
895 "FIDEDUPERANGE".
896
897 "FS_IOC_GETFLAGS", "FS_IOC_SETFLAGS", "FS_IOC_GETVERSION",
898 "FS_IOC_SETVERSION", "FS_IOC_FIEMAP".
899
900 "FS_IOC_FSGETXATTR", "FS_IOC_FSSETXATTR",
901 "FS_IOC_SET_ENCRYPTION_POLICY", "FS_IOC_GET_ENCRYPTION_PWSALT",
902 "FS_IOC_GET_ENCRYPTION_POLICY", "FS_KEY_DESCRIPTOR_SIZE".
903
904 "FS_SECRM_FL", "FS_UNRM_FL", "FS_COMPR_FL", "FS_SYNC_FL",
905 "FS_IMMUTABLE_FL", "FS_APPEND_FL", "FS_NODUMP_FL", "FS_NOATIME_FL",
906 "FS_DIRTY_FL", "FS_COMPRBLK_FL", "FS_NOCOMP_FL", "FS_ENCRYPT_FL",
907 "FS_BTREE_FL", "FS_INDEX_FL", "FS_JOURNAL_DATA_FL", "FS_NOTAIL_FL",
908 "FS_DIRSYNC_FL", "FS_TOPDIR_FL", "FS_FL_USER_MODIFIABLE".
909
910 "FS_XFLAG_REALTIME", "FS_XFLAG_PREALLOC", "FS_XFLAG_IMMUTABLE",
911 "FS_XFLAG_APPEND", "FS_XFLAG_SYNC", "FS_XFLAG_NOATIME",
912 "FS_XFLAG_NODUMP", "FS_XFLAG_RTINHERIT", "FS_XFLAG_PROJINHERIT",
913 "FS_XFLAG_NOSYMLINKS", "FS_XFLAG_EXTSIZE", "FS_XFLAG_EXTSZINHERIT",
914 "FS_XFLAG_NODEFRAG", "FS_XFLAG_FILESTREAM", "FS_XFLAG_DAX",
915 "FS_XFLAG_HASATTR",
916
690 aio_sync $callback->($status) 917 aio_sync $callback->($status)
691 Asynchronously call sync and call the callback when finished. 918 Asynchronously call sync and call the callback when finished.
692 919
693 aio_fsync $fh, $callback->($status) 920 aio_fsync $fh, $callback->($status)
694 Asynchronously call fsync on the given filehandle and call the 921 Asynchronously call fsync on the given filehandle and call the
… …
698 Asynchronously call fdatasync on the given filehandle and call the 925 Asynchronously call fdatasync on the given filehandle and call the
699 callback with the fdatasync result code. 926 callback with the fdatasync result code.
700 927
701 If this call isn't available because your OS lacks it or it couldn't 928 If this call isn't available because your OS lacks it or it couldn't
702 be detected, it will be emulated by calling "fsync" instead. 929 be detected, it will be emulated by calling "fsync" instead.
930
931 aio_syncfs $fh, $callback->($status)
932 Asynchronously call the syncfs syscall to sync the filesystem
933 associated to the given filehandle and call the callback with the
934 syncfs result code. If syncfs is not available, calls sync(), but
935 returns -1 and sets errno to "ENOSYS" nevertheless.
703 936
704 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) 937 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
705 Sync the data portion of the file specified by $offset and $length 938 Sync the data portion of the file specified by $offset and $length
706 to disk (but NOT the metadata), by calling the Linux-specific 939 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 940 sync_file_range call. If sync_file_range is not available or it
… …
711 "IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE", 944 "IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE",
712 "IO::AIO::SYNC_FILE_RANGE_WRITE" and 945 "IO::AIO::SYNC_FILE_RANGE_WRITE" and
713 "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range 946 "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range
714 manpage for details. 947 manpage for details.
715 948
716 aio_pathsync $path, $callback->($status) 949 aio_pathsync $pathname, $callback->($status)
717 This request tries to open, fsync and close the given path. This is 950 This request tries to open, fsync and close the given path. This is
718 a composite request intended to sync directories after directory 951 a composite request intended to sync directories after directory
719 operations (E.g. rename). This might not work on all operating 952 operations (E.g. rename). This might not work on all operating
720 systems or have any specific effect, but usually it makes sure that 953 systems or have any specific effect, but usually it makes sure that
721 directory changes get written to disc. It works for anything that 954 directory changes get written to disc. It works for anything that
… …
724 Future versions of this function might fall back to other methods 957 Future versions of this function might fall back to other methods
725 when "fsync" on the directory fails (such as calling "sync"). 958 when "fsync" on the directory fails (such as calling "sync").
726 959
727 Passes 0 when everything went ok, and -1 on error. 960 Passes 0 when everything went ok, and -1 on error.
728 961
729 aio_msync $scalar, $offset = 0, $length = undef, flags = 0, 962 aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC,
730 $callback->($status) 963 $callback->($status)
731 This is a rather advanced IO::AIO call, which only works on 964 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 965 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, 966 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 967 note that the scalar must only be modified in-place while an aio
… …
736 969
737 It calls the "msync" function of your OS, if available, with the 970 It calls the "msync" function of your OS, if available, with the
738 memory area starting at $offset in the string and ending $length 971 memory area starting at $offset in the string and ending $length
739 bytes later. If $length is negative, counts from the end, and if 972 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 973 $length is "undef", then it goes till the end of the string. The
741 flags can be a combination of "IO::AIO::MS_ASYNC", 974 flags can be either "IO::AIO::MS_ASYNC" or "IO::AIO::MS_SYNC", plus
742 "IO::AIO::MS_INVALIDATE" and "IO::AIO::MS_SYNC". 975 an optional "IO::AIO::MS_INVALIDATE".
743 976
744 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, 977 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0,
745 $callback->($status) 978 $callback->($status)
746 This is a rather advanced IO::AIO call, which works best on 979 This is a rather advanced IO::AIO call, which works best on
747 mmap(2)ed scalars. 980 mmap(2)ed scalars.
748 981
749 It touches (reads or writes) all memory pages in the specified range 982 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 983 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 984 "aio_msync", above, except for flags, which must be either 0 (which
752 reads all pages and ensures they are instantiated) or 985 reads all pages and ensures they are instantiated) or
753 "IO::AIO::MT_MODIFY", which modifies the memory page s(by reading 986 "IO::AIO::MT_MODIFY", which modifies the memory pages (by reading
754 and writing an octet from it, which dirties the page). 987 and writing an octet from it, which dirties the page).
988
989 aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
990 This is a rather advanced IO::AIO call, which works best on
991 mmap(2)ed scalars.
992
993 It reads in all the pages of the underlying storage into memory (if
994 any) and locks them, so they are not getting swapped/paged out or
995 removed.
996
997 If $length is undefined, then the scalar will be locked till the
998 end.
999
1000 On systems that do not implement "mlock", this function returns -1
1001 and sets errno to "ENOSYS".
1002
1003 Note that the corresponding "munlock" is synchronous and is
1004 documented under "MISCELLANEOUS FUNCTIONS".
1005
1006 Example: open a file, mmap and mlock it - both will be undone when
1007 $data gets destroyed.
1008
1009 open my $fh, "<", $path or die "$path: $!";
1010 my $data;
1011 IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
1012 aio_mlock $data; # mlock in background
1013
1014 aio_mlockall $flags, $callback->($status)
1015 Calls the "mlockall" function with the given $flags (a combination
1016 of "IO::AIO::MCL_CURRENT" and "IO::AIO::MCL_FUTURE").
1017
1018 On systems that do not implement "mlockall", this function returns
1019 -1 and sets errno to "ENOSYS".
1020
1021 Note that the corresponding "munlockall" is synchronous and is
1022 documented under "MISCELLANEOUS FUNCTIONS".
1023
1024 Example: asynchronously lock all current and future pages into
1025 memory.
1026
1027 aio_mlockall IO::AIO::MCL_FUTURE;
1028
1029 aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
1030 Queries the extents of the given file (by calling the Linux "FIEMAP"
1031 ioctl, see <http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for
1032 details). If the ioctl is not available on your OS, then this
1033 request will fail with "ENOSYS".
1034
1035 $start is the starting offset to query extents for, $length is the
1036 size of the range to query - if it is "undef", then the whole file
1037 will be queried.
1038
1039 $flags is a combination of flags ("IO::AIO::FIEMAP_FLAG_SYNC" or
1040 "IO::AIO::FIEMAP_FLAG_XATTR" - "IO::AIO::FIEMAP_FLAGS_COMPAT" is
1041 also exported), and is normally 0 or "IO::AIO::FIEMAP_FLAG_SYNC" to
1042 query the data portion.
1043
1044 $count is the maximum number of extent records to return. If it is
1045 "undef", then IO::AIO queries all extents of the range. As a very
1046 special case, if it is 0, then the callback receives the number of
1047 extents instead of the extents themselves (which is unreliable, see
1048 below).
1049
1050 If an error occurs, the callback receives no arguments. The special
1051 "errno" value "IO::AIO::EBADR" is available to test for flag errors.
1052
1053 Otherwise, the callback receives an array reference with extent
1054 structures. Each extent structure is an array reference itself, with
1055 the following members:
1056
1057 [$logical, $physical, $length, $flags]
1058
1059 Flags is any combination of the following flag values (typically
1060 either 0 or "IO::AIO::FIEMAP_EXTENT_LAST" (1)):
1061
1062 "IO::AIO::FIEMAP_EXTENT_LAST", "IO::AIO::FIEMAP_EXTENT_UNKNOWN",
1063 "IO::AIO::FIEMAP_EXTENT_DELALLOC", "IO::AIO::FIEMAP_EXTENT_ENCODED",
1064 "IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED",
1065 "IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED",
1066 "IO::AIO::FIEMAP_EXTENT_DATA_INLINE",
1067 "IO::AIO::FIEMAP_EXTENT_DATA_TAIL",
1068 "IO::AIO::FIEMAP_EXTENT_UNWRITTEN", "IO::AIO::FIEMAP_EXTENT_MERGED"
1069 or "IO::AIO::FIEMAP_EXTENT_SHARED".
1070
1071 At the time of this writing (Linux 3.2), this request is unreliable
1072 unless $count is "undef", as the kernel has all sorts of bugs
1073 preventing it to return all extents of a range for files with a
1074 large number of extents. The code (only) works around all these
1075 issues if $count is "undef".
755 1076
756 aio_group $callback->(...) 1077 aio_group $callback->(...)
757 This is a very special aio request: Instead of doing something, it 1078 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 1079 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 1080 to bundle many requests into a single, composite, request with a
… …
793 While it is theoretically handy to have simple I/O scheduling 1114 While it is theoretically handy to have simple I/O scheduling
794 requests like sleep and file handle readable/writable, the overhead 1115 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 1116 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 1117 not use this function except to put your application under
797 artificial I/O pressure. 1118 artificial I/O pressure.
1119
1120 IO::AIO::WD - multiple working directories
1121 Your process only has one current working directory, which is used by
1122 all threads. This makes it hard to use relative paths (some other
1123 component could call "chdir" at any time, and it is hard to control when
1124 the path will be used by IO::AIO).
1125
1126 One solution for this is to always use absolute paths. This usually
1127 works, but can be quite slow (the kernel has to walk the whole path on
1128 every access), and can also be a hassle to implement.
1129
1130 Newer POSIX systems have a number of functions (openat, fdopendir,
1131 futimensat and so on) that make it possible to specify working
1132 directories per operation.
1133
1134 For portability, and because the clowns who "designed", or shall I
1135 write, perpetrated this new interface were obviously half-drunk, this
1136 abstraction cannot be perfect, though.
1137
1138 IO::AIO allows you to convert directory paths into a so-called
1139 IO::AIO::WD object. This object stores the canonicalised, absolute
1140 version of the path, and on systems that allow it, also a directory file
1141 descriptor.
1142
1143 Everywhere where a pathname is accepted by IO::AIO (e.g. in "aio_stat"
1144 or "aio_unlink"), one can specify an array reference with an IO::AIO::WD
1145 object and a pathname instead (or the IO::AIO::WD object alone, which
1146 gets interpreted as "[$wd, "."]"). If the pathname is absolute, the
1147 IO::AIO::WD object is ignored, otherwise the pathname is resolved
1148 relative to that IO::AIO::WD object.
1149
1150 For example, to get a wd object for /etc and then stat passwd inside,
1151 you would write:
1152
1153 aio_wd "/etc", sub {
1154 my $etcdir = shift;
1155
1156 # although $etcdir can be undef on error, there is generally no reason
1157 # to check for errors here, as aio_stat will fail with ENOENT
1158 # when $etcdir is undef.
1159
1160 aio_stat [$etcdir, "passwd"], sub {
1161 # yay
1162 };
1163 };
1164
1165 The fact that "aio_wd" is a request and not a normal function shows that
1166 creating an IO::AIO::WD object is itself a potentially blocking
1167 operation, which is why it is done asynchronously.
1168
1169 To stat the directory obtained with "aio_wd" above, one could write
1170 either of the following three request calls:
1171
1172 aio_lstat "/etc" , sub { ... # pathname as normal string
1173 aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
1174 aio_lstat $wd , sub { ... # shorthand for the previous
1175
1176 As with normal pathnames, IO::AIO keeps a copy of the working directory
1177 object and the pathname string, so you could write the following without
1178 causing any issues due to $path getting reused:
1179
1180 my $path = [$wd, undef];
1181
1182 for my $name (qw(abc def ghi)) {
1183 $path->[1] = $name;
1184 aio_stat $path, sub {
1185 # ...
1186 };
1187 }
1188
1189 There are some caveats: when directories get renamed (or deleted), the
1190 pathname string doesn't change, so will point to the new directory (or
1191 nowhere at all), while the directory fd, if available on the system,
1192 will still point to the original directory. Most functions accepting a
1193 pathname will use the directory fd on newer systems, and the string on
1194 older systems. Some functions (such as "aio_realpath") will always rely
1195 on the string form of the pathname.
1196
1197 So this functionality is mainly useful to get some protection against
1198 "chdir", to easily get an absolute path out of a relative path for
1199 future reference, and to speed up doing many operations in the same
1200 directory (e.g. when stat'ing all files in a directory).
1201
1202 The following functions implement this working directory abstraction:
1203
1204 aio_wd $pathname, $callback->($wd)
1205 Asynchonously canonicalise the given pathname and convert it to an
1206 IO::AIO::WD object representing it. If possible and supported on the
1207 system, also open a directory fd to speed up pathname resolution
1208 relative to this working directory.
1209
1210 If something goes wrong, then "undef" is passwd to the callback
1211 instead of a working directory object and $! is set appropriately.
1212 Since passing "undef" as working directory component of a pathname
1213 fails the request with "ENOENT", there is often no need for error
1214 checking in the "aio_wd" callback, as future requests using the
1215 value will fail in the expected way.
1216
1217 IO::AIO::CWD
1218 This is a compiletime constant (object) that represents the process
1219 current working directory.
1220
1221 Specifying this object as working directory object for a pathname is
1222 as if the pathname would be specified directly, without a directory
1223 object. For example, these calls are functionally identical:
1224
1225 aio_stat "somefile", sub { ... };
1226 aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
1227
1228 To recover the path associated with an IO::AIO::WD object, you can use
1229 "aio_realpath":
1230
1231 aio_realpath $wd, sub {
1232 warn "path is $_[0]\n";
1233 };
1234
1235 Currently, "aio_statvfs" always, and "aio_rename" and "aio_rmdir"
1236 sometimes, fall back to using an absolue path.
798 1237
799 IO::AIO::REQ CLASS 1238 IO::AIO::REQ CLASS
800 All non-aggregate "aio_*" functions return an object of this class when 1239 All non-aggregate "aio_*" functions return an object of this class when
801 called in non-void context. 1240 called in non-void context.
802 1241
… …
902 Sets a feeder/generator on this group: every group can have an 1341 Sets a feeder/generator on this group: every group can have an
903 attached generator that generates requests if idle. The idea behind 1342 attached generator that generates requests if idle. The idea behind
904 this is that, although you could just queue as many requests as you 1343 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 1344 want in a group, this might starve other requests for a potentially
906 long time. For example, "aio_scandir" might generate hundreds of 1345 long time. For example, "aio_scandir" might generate hundreds of
907 thousands "aio_stat" requests, delaying any later requests for a 1346 thousands of "aio_stat" requests, delaying any later requests for a
908 long time. 1347 long time.
909 1348
910 To avoid this, and allow incremental generation of requests, you can 1349 To avoid this, and allow incremental generation of requests, you can
911 instead a group and set a feeder on it that generates those 1350 instead a group and set a feeder on it that generates those
912 requests. The feed callback will be called whenever there are few 1351 requests. The feed callback will be called whenever there are few
… …
954 results. 1393 results.
955 1394
956 See "poll_cb" for an example. 1395 See "poll_cb" for an example.
957 1396
958 IO::AIO::poll_cb 1397 IO::AIO::poll_cb
959 Process some outstanding events on the result pipe. You have to call 1398 Process some requests that have reached the result phase (i.e. they
960 this regularly. Returns 0 if all events could be processed, or -1 if 1399 have been executed but the results are not yet reported). You have
961 it returned earlier for whatever reason. Returns immediately when no 1400 to call this "regularly" to finish outstanding requests.
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 1401
1402 Returns 0 if all events could be processed (or there were no events
1403 to process), or -1 if it returned earlier for whatever reason.
1404 Returns immediately when no events are outstanding. The amount of
1405 events processed depends on the settings of "IO::AIO::max_poll_req",
1406 "IO::AIO::max_poll_time" and "IO::AIO::max_outstanding".
1407
966 If not all requests were processed for whatever reason, the 1408 If not all requests were processed for whatever reason, the poll
967 filehandle will still be ready when "poll_cb" returns, so normally 1409 file descriptor will still be ready when "poll_cb" returns, so
968 you don't have to do anything special to have it called later. 1410 normally you don't have to do anything special to have it called
1411 later.
1412
1413 Apart from calling "IO::AIO::poll_cb" when the event filehandle
1414 becomes ready, it can be beneficial to call this function from loops
1415 which submit a lot of requests, to make sure the results get
1416 processed when they become available and not just when the loop is
1417 finished and the event loop takes over again. This function returns
1418 very fast when there are no outstanding requests.
969 1419
970 Example: Install an Event watcher that automatically calls 1420 Example: Install an Event watcher that automatically calls
971 IO::AIO::poll_cb with high priority (more examples can be found in 1421 IO::AIO::poll_cb with high priority (more examples can be found in
972 the SYNOPSIS section, at the top of this document): 1422 the SYNOPSIS section, at the top of this document):
973 1423
974 Event->io (fd => IO::AIO::poll_fileno, 1424 Event->io (fd => IO::AIO::poll_fileno,
975 poll => 'r', async => 1, 1425 poll => 'r', async => 1,
976 cb => \&IO::AIO::poll_cb); 1426 cb => \&IO::AIO::poll_cb);
977 1427
978 IO::AIO::poll_wait 1428 IO::AIO::poll_wait
979 If there are any outstanding requests and none of them in the result 1429 Wait until either at least one request is in the result phase or no
980 phase, wait till the result filehandle becomes ready for reading 1430 requests are outstanding anymore.
981 (simply does a "select" on the filehandle. This is useful if you 1431
982 want to synchronously wait for some requests to finish). 1432 This is useful if you want to synchronously wait for some requests
1433 to become ready, without actually handling them.
983 1434
984 See "nreqs" for an example. 1435 See "nreqs" for an example.
985 1436
986 IO::AIO::poll 1437 IO::AIO::poll
987 Waits until some requests have been handled. 1438 Waits until some requests have been handled.
… …
1067 1518
1068 Under normal circumstances you don't need to call this function. 1519 Under normal circumstances you don't need to call this function.
1069 1520
1070 IO::AIO::max_idle $nthreads 1521 IO::AIO::max_idle $nthreads
1071 Limit the number of threads (default: 4) that are allowed to idle 1522 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 1523 (i.e., threads that did not get a request to process within the idle
1073 seconds). That means if a thread becomes idle while $nthreads other 1524 timeout (default: 10 seconds). That means if a thread becomes idle
1074 threads are also idle, it will free its resources and exit. 1525 while $nthreads other threads are also idle, it will free its
1526 resources and exit.
1075 1527
1076 This is useful when you allow a large number of threads (e.g. 100 or 1528 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 1529 1000) to allow for extremely high load situations, but want to free
1078 resources under normal circumstances (1000 threads can easily 1530 resources under normal circumstances (1000 threads can easily
1079 consume 30MB of RAM). 1531 consume 30MB of RAM).
1080 1532
1081 The default is probably ok in most situations, especially if thread 1533 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 1534 creation is fast. If thread creation is very slow on your system you
1083 might want to use larger values. 1535 might want to use larger values.
1084 1536
1537 IO::AIO::idle_timeout $seconds
1538 Sets the minimum idle timeout (default 10) after which worker
1539 threads are allowed to exit. SEe "IO::AIO::max_idle".
1540
1085 IO::AIO::max_outstanding $maxreqs 1541 IO::AIO::max_outstanding $maxreqs
1542 Sets the maximum number of outstanding requests to $nreqs. If you do
1543 queue up more than this number of requests, the next call to
1544 "IO::AIO::poll_cb" (and other functions calling "poll_cb", such as
1545 "IO::AIO::flush" or "IO::AIO::poll") will block until the limit is
1546 no longer exceeded.
1547
1548 In other words, this setting does not enforce a queue limit, but can
1549 be used to make poll functions block if the limit is exceeded.
1550
1086 This is a very bad function to use in interactive programs because 1551 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 1552 it blocks, and a bad way to reduce concurrency because it is
1088 inexact: Better use an "aio_group" together with a feed callback. 1553 inexact: Better use an "aio_group" together with a feed callback.
1089 1554
1090 Sets the maximum number of outstanding requests to $nreqs. If you do 1555 Its main use is in scripts without an event loop - when you want to
1091 queue up more than this number of requests, the next call to the 1556 stat a lot of files, you can write something like this:
1092 "poll_cb" (and "poll_some" and other functions calling "poll_cb")
1093 function will block until the limit is no longer exceeded.
1094 1557
1095 The default value is very large, so there is no practical limit on 1558 IO::AIO::max_outstanding 32;
1559
1560 for my $path (...) {
1561 aio_stat $path , ...;
1562 IO::AIO::poll_cb;
1563 }
1564
1565 IO::AIO::flush;
1566
1567 The call to "poll_cb" inside the loop will normally return
1568 instantly, but as soon as more thna 32 reqeusts are in-flight, it
1569 will block until some requests have been handled. This keeps the
1570 loop from pushing a large number of "aio_stat" requests onto the
1571 queue.
1572
1573 The default value for "max_outstanding" is very large, so there is
1096 the number of outstanding requests. 1574 no practical limit on the number of outstanding requests.
1097
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 1575
1103 STATISTICAL INFORMATION 1576 STATISTICAL INFORMATION
1104 IO::AIO::nreqs 1577 IO::AIO::nreqs
1105 Returns the number of requests currently in the ready, execute or 1578 Returns the number of requests currently in the ready, execute or
1106 pending states (i.e. for which their callback has not been invoked 1579 pending states (i.e. for which their callback has not been invoked
… …
1118 IO::AIO::npending 1591 IO::AIO::npending
1119 Returns the number of requests currently in the pending state 1592 Returns the number of requests currently in the pending state
1120 (executed, but not yet processed by poll_cb). 1593 (executed, but not yet processed by poll_cb).
1121 1594
1122 MISCELLANEOUS FUNCTIONS 1595 MISCELLANEOUS FUNCTIONS
1123 IO::AIO implements some functions that might be useful, but are not 1596 IO::AIO implements some functions that are useful when you want to use
1124 asynchronous. 1597 some "Advanced I/O" function not available to in Perl, without going the
1598 "Asynchronous I/O" route. Many of these have an asynchronous "aio_*"
1599 counterpart.
1600
1601 $numfd = IO::AIO::get_fdlimit
1602 This function is *EXPERIMENTAL* and subject to change.
1603
1604 Tries to find the current file descriptor limit and returns it, or
1605 "undef" and sets $! in case of an error. The limit is one larger
1606 than the highest valid file descriptor number.
1607
1608 IO::AIO::min_fdlimit [$numfd]
1609 This function is *EXPERIMENTAL* and subject to change.
1610
1611 Try to increase the current file descriptor limit(s) to at least
1612 $numfd by changing the soft or hard file descriptor resource limit.
1613 If $numfd is missing, it will try to set a very high limit, although
1614 this is not recommended when you know the actual minimum that you
1615 require.
1616
1617 If the limit cannot be raised enough, the function makes a
1618 best-effort attempt to increase the limit as much as possible, using
1619 various tricks, while still failing. You can query the resulting
1620 limit using "IO::AIO::get_fdlimit".
1621
1622 If an error occurs, returns "undef" and sets $!, otherwise returns
1623 true.
1125 1624
1126 IO::AIO::sendfile $ofh, $ifh, $offset, $count 1625 IO::AIO::sendfile $ofh, $ifh, $offset, $count
1127 Calls the "eio_sendfile_sync" function, which is like 1626 Calls the "eio_sendfile_sync" function, which is like
1128 "aio_sendfile", but is blocking (this makes most sense if you know 1627 "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 1628 the input data is likely cached already and the output filehandle is
1130 set to non-blocking operations). 1629 set to non-blocking operations).
1131 1630
1132 Returns the number of bytes copied, or -1 on error. 1631 Returns the number of bytes copied, or -1 on error.
1133 1632
1134 IO::AIO::fadvise $fh, $offset, $len, $advice 1633 IO::AIO::fadvise $fh, $offset, $len, $advice
1135 Simply calls the "posix_fadvise" function (see it's manpage for 1634 Simply calls the "posix_fadvise" function (see its manpage for
1136 details). The following advice constants are avaiable: 1635 details). The following advice constants are available:
1137 "IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL", 1636 "IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL",
1138 "IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE", 1637 "IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE",
1139 "IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED". 1638 "IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED".
1140 1639
1141 On systems that do not implement "posix_fadvise", this function 1640 On systems that do not implement "posix_fadvise", this function
1142 returns ENOSYS, otherwise the return value of "posix_fadvise". 1641 returns ENOSYS, otherwise the return value of "posix_fadvise".
1143 1642
1643 IO::AIO::madvise $scalar, $offset, $len, $advice
1644 Simply calls the "posix_madvise" function (see its manpage for
1645 details). The following advice constants are available:
1646 "IO::AIO::MADV_NORMAL", "IO::AIO::MADV_SEQUENTIAL",
1647 "IO::AIO::MADV_RANDOM", "IO::AIO::MADV_WILLNEED",
1648 "IO::AIO::MADV_DONTNEED".
1649
1650 If $offset is negative, counts from the end. If $length is negative,
1651 the remaining length of the $scalar is used. If possible, $length
1652 will be reduced to fit into the $scalar.
1653
1654 On systems that do not implement "posix_madvise", this function
1655 returns ENOSYS, otherwise the return value of "posix_madvise".
1656
1657 IO::AIO::mprotect $scalar, $offset, $len, $protect
1658 Simply calls the "mprotect" function on the preferably AIO::mmap'ed
1659 $scalar (see its manpage for details). The following protect
1660 constants are available: "IO::AIO::PROT_NONE", "IO::AIO::PROT_READ",
1661 "IO::AIO::PROT_WRITE", "IO::AIO::PROT_EXEC".
1662
1663 If $offset is negative, counts from the end. If $length is negative,
1664 the remaining length of the $scalar is used. If possible, $length
1665 will be reduced to fit into the $scalar.
1666
1667 On systems that do not implement "mprotect", this function returns
1668 ENOSYS, otherwise the return value of "mprotect".
1669
1144 IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset] 1670 IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
1145 Memory-maps a file (or anonymous memory range) and attaches it to 1671 Memory-maps a file (or anonymous memory range) and attaches it to
1146 the given $scalar, which will act like a string scalar. 1672 the given $scalar, which will act like a string scalar. Returns true
1673 on success, and false otherwise.
1147 1674
1675 The scalar must exist, but its contents do not matter - this means
1676 you cannot use a nonexistant array or hash element. When in doubt,
1677 "undef" the scalar first.
1678
1148 The only operations allowed on the scalar are "substr"/"vec" that 1679 The only operations allowed on the mmapped scalar are
1149 don't change the string length, and most read-only operations such 1680 "substr"/"vec", which don't change the string length, and most
1150 as copying it or searching it with regexes and so on. 1681 read-only operations such as copying it or searching it with regexes
1682 and so on.
1151 1683
1152 Anything else is unsafe and will, at best, result in memory leaks. 1684 Anything else is unsafe and will, at best, result in memory leaks.
1153 1685
1154 The memory map associated with the $scalar is automatically removed 1686 The memory map associated with the $scalar is automatically removed
1155 when the $scalar is destroyed, or when the "IO::AIO::mmap" or 1687 when the $scalar is undef'd or destroyed, or when the
1156 "IO::AIO::munmap" functions are called. 1688 "IO::AIO::mmap" or "IO::AIO::munmap" functions are called on it.
1157 1689
1158 This calls the "mmap"(2) function internally. See your system's 1690 This calls the "mmap"(2) function internally. See your system's
1159 manual page for details on the $length, $prot and $flags parameters. 1691 manual page for details on the $length, $prot and $flags parameters.
1160 1692
1161 The $length must be larger than zero and smaller than the actual 1693 The $length must be larger than zero and smaller than the actual
… …
1165 "IO::AIO::PROT_EXEC", "IO::AIO::PROT_READ" and/or 1697 "IO::AIO::PROT_EXEC", "IO::AIO::PROT_READ" and/or
1166 "IO::AIO::PROT_WRITE", 1698 "IO::AIO::PROT_WRITE",
1167 1699
1168 $flags can be a combination of "IO::AIO::MAP_SHARED" or 1700 $flags can be a combination of "IO::AIO::MAP_SHARED" or
1169 "IO::AIO::MAP_PRIVATE", or a number of system-specific flags (when 1701 "IO::AIO::MAP_PRIVATE", or a number of system-specific flags (when
1170 not available, the are defined as 0): "IO::AIO::MAP_ANONYMOUS" 1702 not available, the are 0): "IO::AIO::MAP_ANONYMOUS" (which is set to
1171 (which is set to "MAP_ANON" if your system only provides this 1703 "MAP_ANON" if your system only provides this constant),
1704 "IO::AIO::MAP_LOCKED", "IO::AIO::MAP_NORESERVE",
1172 constant), "IO::AIO::MAP_HUGETLB", "IO::AIO::MAP_LOCKED", 1705 "IO::AIO::MAP_POPULATE", "IO::AIO::MAP_NONBLOCK",
1706 "IO::AIO::MAP_FIXED", "IO::AIO::MAP_GROWSDOWN",
1173 "IO::AIO::MAP_NORESERVE", "IO::AIO::MAP_POPULATE" or 1707 "IO::AIO::MAP_32BIT", "IO::AIO::MAP_HUGETLB" or
1174 "IO::AIO::MAP_NONBLOCK" 1708 "IO::AIO::MAP_STACK".
1175 1709
1176 If $fh is "undef", then a file descriptor of -1 is passed. 1710 If $fh is "undef", then a file descriptor of -1 is passed.
1177 1711
1178 $offset is the offset from the start of the file - it generally must 1712 $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. 1713 be a multiple of "IO::AIO::PAGESIZE" and defaults to 0.
… …
1192 my $fast_md5 = md5 $data; 1726 my $fast_md5 = md5 $data;
1193 1727
1194 IO::AIO::munmap $scalar 1728 IO::AIO::munmap $scalar
1195 Removes a previous mmap and undefines the $scalar. 1729 Removes a previous mmap and undefines the $scalar.
1196 1730
1197 IO::AIO::mlockall $flags 1731 IO::AIO::mremap $scalar, $new_length, $flags = MREMAP_MAYMOVE[,
1198 Calls the "mlockall" function with the given $flags (a combination 1732 $new_address = 0]
1199 of "IO::AIO::MCL_CURRENT" and "IO::AIO::MCL__FUTURE"). 1733 Calls the Linux-specific mremap(2) system call. The $scalar must
1734 have been mapped by "IO::AIO::mmap", and $flags must currently
1735 either be 0 or "IO::AIO::MREMAP_MAYMOVE".
1200 1736
1201 On systems that do not implement "mlockall", this function returns 1737 Returns true if successful, and false otherwise. If the underlying
1202 ENOSYS, otherwise the return value of "mlockall". 1738 mmapped region has changed address, then the true value has the
1739 numerical value 1, otherwise it has the numerical value 0:
1740
1741 my $success = IO::AIO::mremap $mmapped, 8192, IO::AIO::MREMAP_MAYMOVE
1742 or die "mremap: $!";
1743
1744 if ($success*1) {
1745 warn "scalar has chanegd address in memory\n";
1746 }
1747
1748 "IO::AIO::MREMAP_FIXED" and the $new_address argument are currently
1749 implemented, but not supported and might go away in a future
1750 version.
1751
1752 On systems where this call is not supported or is not emulated, this
1753 call returns falls and sets $! to "ENOSYS".
1754
1755 IO::AIO::munlock $scalar, $offset = 0, $length = undef
1756 Calls the "munlock" function, undoing the effects of a previous
1757 "aio_mlock" call (see its description for details).
1203 1758
1204 IO::AIO::munlockall 1759 IO::AIO::munlockall
1205 Calls the "munlockall" function. 1760 Calls the "munlockall" function.
1206 1761
1207 On systems that do not implement "munlockall", this function returns 1762 On systems that do not implement "munlockall", this function returns
1208 ENOSYS, otherwise the return value of "munlockall". 1763 ENOSYS, otherwise the return value of "munlockall".
1764
1765 IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
1766 Calls the GNU/Linux splice(2) syscall, if available. If $r_off or
1767 $w_off are "undef", then "NULL" is passed for these, otherwise they
1768 should be the file offset.
1769
1770 $r_fh and $w_fh should not refer to the same file, as splice might
1771 silently corrupt the data in this case.
1772
1773 The following symbol flag values are available:
1774 "IO::AIO::SPLICE_F_MOVE", "IO::AIO::SPLICE_F_NONBLOCK",
1775 "IO::AIO::SPLICE_F_MORE" and "IO::AIO::SPLICE_F_GIFT".
1776
1777 See the splice(2) manpage for details.
1778
1779 IO::AIO::tee $r_fh, $w_fh, $length, $flags
1780 Calls the GNU/Linux tee(2) syscall, see its manpage and the
1781 description for "IO::AIO::splice" above for details.
1782
1783 $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
1784 Attempts to query or change the pipe buffer size. Obviously works
1785 only on pipes, and currently works only on GNU/Linux systems, and
1786 fails with -1/"ENOSYS" everywhere else. If anybody knows how to
1787 influence pipe buffer size on other systems, drop me a note.
1788
1789 ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
1790 This is a direct interface to the Linux pipe2(2) system call. If
1791 $flags is missing or 0, then this should be the same as a call to
1792 perl's built-in "pipe" function and create a new pipe, and works on
1793 systems that lack the pipe2 syscall. On win32, this case invokes
1794 "_pipe (..., 4096, O_BINARY)".
1795
1796 If $flags is non-zero, it tries to invoke the pipe2 system call with
1797 the given flags (Linux 2.6.27, glibc 2.9).
1798
1799 On success, the read and write file handles are returned.
1800
1801 On error, nothing will be returned. If the pipe2 syscall is missing
1802 and $flags is non-zero, fails with "ENOSYS".
1803
1804 Please refer to pipe2(2) for more info on the $flags, but at the
1805 time of this writing, "IO::AIO::O_CLOEXEC", "IO::AIO::O_NONBLOCK"
1806 and "IO::AIO::O_DIRECT" (Linux 3.4, for packet-based pipes) were
1807 supported.
1808
1809 Example: create a pipe race-free w.r.t. threads and fork:
1810
1811 my ($rfh, $wfh) = IO::AIO::pipe2 IO::AIO::O_CLOEXEC
1812 or die "pipe2: $!\n";
1813
1814 $fh = IO::AIO::eventfd [$initval, [$flags]]
1815 This is a direct interface to the Linux eventfd(2) system call. The
1816 (unhelpful) defaults for $initval and $flags are 0 for both.
1817
1818 On success, the new eventfd filehandle is returned, otherwise
1819 returns "undef". If the eventfd syscall is missing, fails with
1820 "ENOSYS".
1821
1822 Please refer to eventfd(2) for more info on this call.
1823
1824 The following symbol flag values are available:
1825 "IO::AIO::EFD_CLOEXEC", "IO::AIO::EFD_NONBLOCK" and
1826 "IO::AIO::EFD_SEMAPHORE" (Linux 2.6.30).
1827
1828 Example: create a new eventfd filehandle:
1829
1830 $fh = IO::AIO::eventfd 0, IO::AIO::O_CLOEXEC
1831 or die "eventfd: $!\n";
1832
1833 $fh = IO::AIO::timerfd_create $clockid[, $flags]
1834 This is a direct interface to the Linux timerfd_create(2) system
1835 call. The (unhelpful) default for $flags is 0.
1836
1837 On success, the new timerfd filehandle is returned, otherwise
1838 returns "undef". If the eventfd syscall is missing, fails with
1839 "ENOSYS".
1840
1841 Please refer to timerfd_create(2) for more info on this call.
1842
1843 The following $clockid values are available:
1844 "IO::AIO::CLOCK_REALTIME", "IO::AIO::CLOCK_MONOTONIC"
1845 "IO::AIO::CLOCK_CLOCK_BOOTTIME" (Linux 3.15)
1846 "IO::AIO::CLOCK_CLOCK_REALTIME_ALARM" (Linux 3.11) and
1847 "IO::AIO::CLOCK_CLOCK_BOOTTIME_ALARM" (Linux 3.11).
1848
1849 The following $flags values are available (Linux 2.6.27):
1850 "IO::AIO::TFD_NONBLOCK" and "IO::AIO::TFD_CLOEXEC".
1851
1852 Example: create a new timerfd and set it to one-second repeated
1853 alarms, then wait for two alarms:
1854
1855 my $fh = IO::AIO::timerfd_create IO::AIO::CLOCK_BOOTTIME, IO::AIO::TFD_CLOEXEC
1856 or die "timerfd_create: $!\n";
1857
1858 defined IO::AIO::timerfd_settime $fh, 0, 1, 1
1859 or die "timerfd_settime: $!\n";
1860
1861 for (1..2) {
1862 8 == sysread $fh, my $buf, 8
1863 or die "timerfd read failure\n";
1864
1865 printf "number of expirations (likely 1): %d\n",
1866 unpack "Q", $buf;
1867 }
1868
1869 ($cur_interval, $cur_value) = IO::AIO::timerfd_settime $fh, $flags,
1870 $new_interval, $nbw_value
1871 This is a direct interface to the Linux timerfd_settime(2) system
1872 call. Please refer to its manpage for more info on this call.
1873
1874 The new itimerspec is specified using two (possibly fractional)
1875 second values, $new_interval and $new_value).
1876
1877 On success, the current interval and value are returned (as per
1878 "timerfd_gettime"). On failure, the empty list is returned.
1879
1880 The following $flags values are available:
1881 "IO::AIO::TFD_TIMER_ABSTIME" and "IO::AIO::TFD_TIMER_CANCEL_ON_SET".
1882
1883 See "IO::AIO::timerfd_create" for a full example.
1884
1885 ($cur_interval, $cur_value) = IO::AIO::timerfd_gettime $fh
1886 This is a direct interface to the Linux timerfd_gettime(2) system
1887 call. Please refer to its manpage for more info on this call.
1888
1889 On success, returns the current values of interval and value for the
1890 given timerfd (as potentially fractional second values). On failure,
1891 the empty list is returned.
1209 1892
1210EVENT LOOP INTEGRATION 1893EVENT LOOP INTEGRATION
1211 It is recommended to use AnyEvent::AIO to integrate IO::AIO 1894 It is recommended to use AnyEvent::AIO to integrate IO::AIO
1212 automatically into many event loops: 1895 automatically into many event loops:
1213 1896
… …
1236 # Danga::Socket integration 1919 # Danga::Socket integration
1237 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => 1920 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
1238 \&IO::AIO::poll_cb); 1921 \&IO::AIO::poll_cb);
1239 1922
1240 FORK BEHAVIOUR 1923 FORK BEHAVIOUR
1241 This module should do "the right thing" when the process using it forks: 1924 Usage of pthreads in a program changes the semantics of fork
1925 considerably. Specifically, only async-safe functions can be called
1926 after fork. Perl doesn't know about this, so in general, you cannot call
1927 fork with defined behaviour in perl if pthreads are involved. IO::AIO
1928 uses pthreads, so this applies, but many other extensions and (for
1929 inexplicable reasons) perl itself often is linked against pthreads, so
1930 this limitation applies to quite a lot of perls.
1242 1931
1243 Before the fork, IO::AIO enters a quiescent state where no requests can 1932 This module no longer tries to fight your OS, or POSIX. That means
1244 be added in other threads and no results will be processed. After the 1933 IO::AIO only works in the process that loaded it. Forking is fully
1245 fork the parent simply leaves the quiescent state and continues 1934 supported, but using IO::AIO in the child is not.
1246 request/result processing, while the child frees the request/result
1247 queue (so that the requests started before the fork will only be handled
1248 in the parent). Threads will be started on demand until the limit set in
1249 the parent process has been reached again.
1250 1935
1251 In short: the parent will, after a short pause, continue as if fork had 1936 You might get around by not *using* IO::AIO before (or after) forking.
1252 not been called, while the child will act as if IO::AIO has not been 1937 You could also try to call the IO::AIO::reinit function in the child:
1253 used yet. 1938
1939 IO::AIO::reinit
1940 Abandons all current requests and I/O threads and simply
1941 reinitialises all data structures. This is not an operation
1942 supported by any standards, but happens to work on GNU/Linux and
1943 some newer BSD systems.
1944
1945 The only reasonable use for this function is to call it after
1946 forking, if "IO::AIO" was used in the parent. Calling it while
1947 IO::AIO is active in the process will result in undefined behaviour.
1948 Calling it at any time will also result in any undefined (by POSIX)
1949 behaviour.
1950
1951 LINUX-SPECIFIC CALLS
1952 When a call is documented as "linux-specific" then this means it
1953 originated on GNU/Linux. "IO::AIO" will usually try to autodetect the
1954 availability and compatibility of such calls regardless of the platform
1955 it is compiled on, so platforms such as FreeBSD which often implement
1956 these calls will work. When in doubt, call them and see if they fail wth
1957 "ENOSYS".
1254 1958
1255 MEMORY USAGE 1959 MEMORY USAGE
1256 Per-request usage: 1960 Per-request usage:
1257 1961
1258 Each aio request uses - depending on your architecture - around 100-200 1962 Each aio request uses - depending on your architecture - around 100-200
… …
1269 In the execution phase, some aio requests require more memory for 1973 In the execution phase, some aio requests require more memory for
1270 temporary buffers, and each thread requires a stack and other data 1974 temporary buffers, and each thread requires a stack and other data
1271 structures (usually around 16k-128k, depending on the OS). 1975 structures (usually around 16k-128k, depending on the OS).
1272 1976
1273KNOWN BUGS 1977KNOWN BUGS
1274 Known bugs will be fixed in the next release. 1978 Known bugs will be fixed in the next release :)
1979
1980KNOWN ISSUES
1981 Calls that try to "import" foreign memory areas (such as "IO::AIO::mmap"
1982 or "IO::AIO::aio_slurp") do not work with generic lvalues, such as
1983 non-created hash slots or other scalars I didn't think of. It's best to
1984 avoid such and either use scalar variables or making sure that the
1985 scalar exists (e.g. by storing "undef") and isn't "funny" (e.g. tied).
1986
1987 I am not sure anything can be done about this, so this is considered a
1988 known issue, rather than a bug.
1275 1989
1276SEE ALSO 1990SEE ALSO
1277 AnyEvent::AIO for easy integration into event loops, Coro::AIO for a 1991 AnyEvent::AIO for easy integration into event loops, Coro::AIO for a
1278 more natural syntax. 1992 more natural syntax.
1279 1993

Diff Legend

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