| 1 |
=head1 NAME |
| 2 |
|
| 3 |
IO::AIO - Asynchronous Input/Output |
| 4 |
|
| 5 |
=head1 SYNOPSIS |
| 6 |
|
| 7 |
use IO::AIO; |
| 8 |
|
| 9 |
aio_open "/etc/passwd", O_RDONLY, 0, sub { |
| 10 |
my ($fh) = @_; |
| 11 |
... |
| 12 |
}; |
| 13 |
|
| 14 |
aio_unlink "/tmp/file", sub { }; |
| 15 |
|
| 16 |
aio_read $fh, 30000, 1024, $buffer, 0, sub { |
| 17 |
$_[0] > 0 or die "read error: $!"; |
| 18 |
}; |
| 19 |
|
| 20 |
# Event |
| 21 |
Event->io (fd => IO::AIO::poll_fileno, |
| 22 |
poll => 'r', |
| 23 |
cb => \&IO::AIO::poll_cb); |
| 24 |
|
| 25 |
# Glib/Gtk2 |
| 26 |
add_watch Glib::IO IO::AIO::poll_fileno, |
| 27 |
in => sub { IO::AIO::poll_cb; 1 }; |
| 28 |
|
| 29 |
# Tk |
| 30 |
Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
| 31 |
readable => \&IO::AIO::poll_cb); |
| 32 |
|
| 33 |
# Danga::Socket |
| 34 |
Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
| 35 |
\&IO::AIO::poll_cb); |
| 36 |
|
| 37 |
|
| 38 |
=head1 DESCRIPTION |
| 39 |
|
| 40 |
This module implements asynchronous I/O using whatever means your |
| 41 |
operating system supports. |
| 42 |
|
| 43 |
Currently, a number of threads are started that execute your read/writes |
| 44 |
and signal their completion. You don't need thread support in your libc or |
| 45 |
perl, and the threads created by this module will not be visible to the |
| 46 |
pthreads library. In the future, this module might make use of the native |
| 47 |
aio functions available on many operating systems. However, they are often |
| 48 |
not well-supported (Linux doesn't allow them on normal files currently, |
| 49 |
for example), and they would only support aio_read and aio_write, so the |
| 50 |
remaining functionality would have to be implemented using threads anyway. |
| 51 |
|
| 52 |
Although the module will work with in the presence of other threads, it is |
| 53 |
currently not reentrant, so use appropriate locking yourself, always call |
| 54 |
C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
| 55 |
C<aio_> functions) recursively. |
| 56 |
|
| 57 |
=cut |
| 58 |
|
| 59 |
package IO::AIO; |
| 60 |
|
| 61 |
no warnings; |
| 62 |
|
| 63 |
use base 'Exporter'; |
| 64 |
|
| 65 |
use Fcntl (); |
| 66 |
|
| 67 |
BEGIN { |
| 68 |
$VERSION = 1.5; |
| 69 |
|
| 70 |
@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
| 71 |
aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead); |
| 72 |
@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
| 73 |
|
| 74 |
require XSLoader; |
| 75 |
XSLoader::load IO::AIO, $VERSION; |
| 76 |
} |
| 77 |
|
| 78 |
=head1 FUNCTIONS |
| 79 |
|
| 80 |
=head2 AIO FUNCTIONS |
| 81 |
|
| 82 |
All the C<aio_*> calls are more or less thin wrappers around the syscall |
| 83 |
with the same name (sans C<aio_>). The arguments are similar or identical, |
| 84 |
and they all accept an additional (and optional) C<$callback> argument |
| 85 |
which must be a code reference. This code reference will get called with |
| 86 |
the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
| 87 |
perl, which usually delivers "false") as it's sole argument when the given |
| 88 |
syscall has been executed asynchronously. |
| 89 |
|
| 90 |
All functions expecting a filehandle keep a copy of the filehandle |
| 91 |
internally until the request has finished. |
| 92 |
|
| 93 |
The pathnames you pass to these routines I<must> be absolute and |
| 94 |
encoded in byte form. The reason for the former is that at the time the |
| 95 |
request is being executed, the current working directory could have |
| 96 |
changed. Alternatively, you can make sure that you never change the |
| 97 |
current working directory. |
| 98 |
|
| 99 |
To encode pathnames to byte form, either make sure you either: a) |
| 100 |
always pass in filenames you got from outside (command line, readdir |
| 101 |
etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
| 102 |
your pathnames to the locale (or other) encoding in effect in the user |
| 103 |
environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
| 104 |
use something else. |
| 105 |
|
| 106 |
=over 4 |
| 107 |
|
| 108 |
=item aio_open $pathname, $flags, $mode, $callback |
| 109 |
|
| 110 |
Asynchronously open or create a file and call the callback with a newly |
| 111 |
created filehandle for the file. |
| 112 |
|
| 113 |
The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
| 114 |
for an explanation. |
| 115 |
|
| 116 |
The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
| 117 |
list. They are the same as used by C<sysopen>. |
| 118 |
|
| 119 |
Likewise, C<$mode> specifies the mode of the newly created file, if it |
| 120 |
didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
| 121 |
except that it is mandatory (i.e. use C<0> if you don't create new files, |
| 122 |
and C<0666> or C<0777> if you do). |
| 123 |
|
| 124 |
Example: |
| 125 |
|
| 126 |
aio_open "/etc/passwd", O_RDONLY, 0, sub { |
| 127 |
if ($_[0]) { |
| 128 |
print "open successful, fh is $_[0]\n"; |
| 129 |
... |
| 130 |
} else { |
| 131 |
die "open failed: $!\n"; |
| 132 |
} |
| 133 |
}; |
| 134 |
|
| 135 |
=item aio_close $fh, $callback |
| 136 |
|
| 137 |
Asynchronously close a file and call the callback with the result |
| 138 |
code. I<WARNING:> although accepted, you should not pass in a perl |
| 139 |
filehandle here, as perl will likely close the file descriptor another |
| 140 |
time when the filehandle is destroyed. Normally, you can safely call perls |
| 141 |
C<close> or just let filehandles go out of scope. |
| 142 |
|
| 143 |
This is supposed to be a bug in the API, so that might change. It's |
| 144 |
therefore best to avoid this function. |
| 145 |
|
| 146 |
=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
| 147 |
|
| 148 |
=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
| 149 |
|
| 150 |
Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
| 151 |
into the scalar given by C<data> and offset C<dataoffset> and calls the |
| 152 |
callback without the actual number of bytes read (or -1 on error, just |
| 153 |
like the syscall). |
| 154 |
|
| 155 |
The C<$data> scalar I<MUST NOT> be modified in any way while the request |
| 156 |
is outstanding. Modifying it can result in segfaults or WW3 (if the |
| 157 |
necessary/optional hardware is installed). |
| 158 |
|
| 159 |
Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
| 160 |
offset C<0> within the scalar: |
| 161 |
|
| 162 |
aio_read $fh, 7, 15, $buffer, 0, sub { |
| 163 |
$_[0] > 0 or die "read error: $!"; |
| 164 |
print "read $_[0] bytes: <$buffer>\n"; |
| 165 |
}; |
| 166 |
|
| 167 |
=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback |
| 168 |
|
| 169 |
Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
| 170 |
reading at byte offset C<$in_offset>, and starts writing at the current |
| 171 |
file offset of C<$out_fh>. Because of that, it is not safe to issue more |
| 172 |
than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
| 173 |
other. |
| 174 |
|
| 175 |
This call tries to make use of a native C<sendfile> syscall to provide |
| 176 |
zero-copy operation. For this to work, C<$out_fh> should refer to a |
| 177 |
socket, and C<$in_fh> should refer to mmap'able file. |
| 178 |
|
| 179 |
If the native sendfile call fails or is not implemented, it will be |
| 180 |
emulated, so you can call C<aio_sendfile> on any filehandles regardless of |
| 181 |
the limitations of the OS. |
| 182 |
|
| 183 |
Please note, however, that C<aio_sendfile> can read more bytes from |
| 184 |
C<$in_fh> than are written, and there is no way to find out how many |
| 185 |
bytes have been read form C<aio_sendfile> alone, as C<aio_sendfile> only |
| 186 |
provides the number of bytes written to C<$out_fh>. Only if the return |
| 187 |
value (the value provided to the callback) equals C<$length> one can |
| 188 |
assume that C<$length> bytes have been read. |
| 189 |
|
| 190 |
=item aio_readahead $fh,$offset,$length, $callback |
| 191 |
|
| 192 |
C<aio_readahead> populates the page cache with data from a file so that |
| 193 |
subsequent reads from that file will not block on disk I/O. The C<$offset> |
| 194 |
argument specifies the starting point from which data is to be read and |
| 195 |
C<$length> specifies the number of bytes to be read. I/O is performed in |
| 196 |
whole pages, so that offset is effectively rounded down to a page boundary |
| 197 |
and bytes are read up to the next page boundary greater than or equal to |
| 198 |
(off-set+length). C<aio_readahead> does not read beyond the end of the |
| 199 |
file. The current file offset of the file is left unchanged. |
| 200 |
|
| 201 |
If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
| 202 |
emulated by simply reading the data, which would have a similar effect. |
| 203 |
|
| 204 |
=item aio_stat $fh_or_path, $callback |
| 205 |
|
| 206 |
=item aio_lstat $fh, $callback |
| 207 |
|
| 208 |
Works like perl's C<stat> or C<lstat> in void context. The callback will |
| 209 |
be called after the stat and the results will be available using C<stat _> |
| 210 |
or C<-s _> etc... |
| 211 |
|
| 212 |
The pathname passed to C<aio_stat> must be absolute. See API NOTES, above, |
| 213 |
for an explanation. |
| 214 |
|
| 215 |
Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
| 216 |
error when stat'ing a large file, the results will be silently truncated |
| 217 |
unless perl itself is compiled with large file support. |
| 218 |
|
| 219 |
Example: Print the length of F</etc/passwd>: |
| 220 |
|
| 221 |
aio_stat "/etc/passwd", sub { |
| 222 |
$_[0] and die "stat failed: $!"; |
| 223 |
print "size is ", -s _, "\n"; |
| 224 |
}; |
| 225 |
|
| 226 |
=item aio_unlink $pathname, $callback |
| 227 |
|
| 228 |
Asynchronously unlink (delete) a file and call the callback with the |
| 229 |
result code. |
| 230 |
|
| 231 |
=item aio_rmdir $pathname, $callback |
| 232 |
|
| 233 |
Asynchronously rmdir (delete) a directory and call the callback with the |
| 234 |
result code. |
| 235 |
|
| 236 |
=item aio_fsync $fh, $callback |
| 237 |
|
| 238 |
Asynchronously call fsync on the given filehandle and call the callback |
| 239 |
with the fsync result code. |
| 240 |
|
| 241 |
=item aio_fdatasync $fh, $callback |
| 242 |
|
| 243 |
Asynchronously call fdatasync on the given filehandle and call the |
| 244 |
callback with the fdatasync result code. |
| 245 |
|
| 246 |
If this call isn't available because your OS lacks it or it couldn't be |
| 247 |
detected, it will be emulated by calling C<fsync> instead. |
| 248 |
|
| 249 |
=back |
| 250 |
|
| 251 |
=head2 SUPPORT FUNCTIONS |
| 252 |
|
| 253 |
=over 4 |
| 254 |
|
| 255 |
=item $fileno = IO::AIO::poll_fileno |
| 256 |
|
| 257 |
Return the I<request result pipe file descriptor>. This filehandle must be |
| 258 |
polled for reading by some mechanism outside this module (e.g. Event or |
| 259 |
select, see below or the SYNOPSIS). If the pipe becomes readable you have |
| 260 |
to call C<poll_cb> to check the results. |
| 261 |
|
| 262 |
See C<poll_cb> for an example. |
| 263 |
|
| 264 |
=item IO::AIO::poll_cb |
| 265 |
|
| 266 |
Process all outstanding events on the result pipe. You have to call this |
| 267 |
regularly. Returns the number of events processed. Returns immediately |
| 268 |
when no events are outstanding. |
| 269 |
|
| 270 |
Example: Install an Event watcher that automatically calls |
| 271 |
IO::AIO::poll_cb with high priority: |
| 272 |
|
| 273 |
Event->io (fd => IO::AIO::poll_fileno, |
| 274 |
poll => 'r', async => 1, |
| 275 |
cb => \&IO::AIO::poll_cb); |
| 276 |
|
| 277 |
=item IO::AIO::poll_wait |
| 278 |
|
| 279 |
Wait till the result filehandle becomes ready for reading (simply does a |
| 280 |
C<select> on the filehandle. This is useful if you want to synchronously wait |
| 281 |
for some requests to finish). |
| 282 |
|
| 283 |
See C<nreqs> for an example. |
| 284 |
|
| 285 |
=item IO::AIO::nreqs |
| 286 |
|
| 287 |
Returns the number of requests currently outstanding (i.e. for which their |
| 288 |
callback has not been invoked yet). |
| 289 |
|
| 290 |
Example: wait till there are no outstanding requests anymore: |
| 291 |
|
| 292 |
IO::AIO::poll_wait, IO::AIO::poll_cb |
| 293 |
while IO::AIO::nreqs; |
| 294 |
|
| 295 |
=item IO::AIO::flush |
| 296 |
|
| 297 |
Wait till all outstanding AIO requests have been handled. |
| 298 |
|
| 299 |
Strictly equivalent to: |
| 300 |
|
| 301 |
IO::AIO::poll_wait, IO::AIO::poll_cb |
| 302 |
while IO::AIO::nreqs; |
| 303 |
|
| 304 |
=item IO::AIO::poll |
| 305 |
|
| 306 |
Waits until some requests have been handled. |
| 307 |
|
| 308 |
Strictly equivalent to: |
| 309 |
|
| 310 |
IO::AIO::poll_wait, IO::AIO::poll_cb |
| 311 |
if IO::AIO::nreqs; |
| 312 |
|
| 313 |
=item IO::AIO::min_parallel $nthreads |
| 314 |
|
| 315 |
Set the minimum number of AIO threads to C<$nthreads>. The current default |
| 316 |
is C<4>, which means four asynchronous operations can be done at one time |
| 317 |
(the number of outstanding operations, however, is unlimited). |
| 318 |
|
| 319 |
IO::AIO starts threads only on demand, when an AIO request is queued and |
| 320 |
no free thread exists. |
| 321 |
|
| 322 |
It is recommended to keep the number of threads low, as some Linux |
| 323 |
kernel versions will scale negatively with the number of threads (higher |
| 324 |
parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
| 325 |
threads should be fine. |
| 326 |
|
| 327 |
Under most circumstances you don't need to call this function, as the |
| 328 |
module selects a default that is suitable for low to moderate load. |
| 329 |
|
| 330 |
=item IO::AIO::max_parallel $nthreads |
| 331 |
|
| 332 |
Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
| 333 |
specified number of threads are currently running, this function kills |
| 334 |
them. This function blocks until the limit is reached. |
| 335 |
|
| 336 |
While C<$nthreads> are zero, aio requests get queued but not executed |
| 337 |
until the number of threads has been increased again. |
| 338 |
|
| 339 |
This module automatically runs C<max_parallel 0> at program end, to ensure |
| 340 |
that all threads are killed and that there are no outstanding requests. |
| 341 |
|
| 342 |
Under normal circumstances you don't need to call this function. |
| 343 |
|
| 344 |
=item $oldnreqs = IO::AIO::max_outstanding $nreqs |
| 345 |
|
| 346 |
Sets the maximum number of outstanding requests to C<$nreqs>. If you |
| 347 |
try to queue up more than this number of requests, the caller will block until |
| 348 |
some requests have been handled. |
| 349 |
|
| 350 |
The default is very large, so normally there is no practical limit. If you |
| 351 |
queue up many requests in a loop it often improves speed if you set |
| 352 |
this to a relatively low number, such as C<100>. |
| 353 |
|
| 354 |
Under normal circumstances you don't need to call this function. |
| 355 |
|
| 356 |
=back |
| 357 |
|
| 358 |
=cut |
| 359 |
|
| 360 |
# support function to convert a fd into a perl filehandle |
| 361 |
sub _fd2fh { |
| 362 |
return undef if $_[0] < 0; |
| 363 |
|
| 364 |
# try to generate nice filehandles |
| 365 |
my $sym = "IO::AIO::fd#$_[0]"; |
| 366 |
local *$sym; |
| 367 |
|
| 368 |
open *$sym, "+<&=$_[0]" # usually works under any unix |
| 369 |
or open *$sym, "<&=$_[0]" # cygwin needs this |
| 370 |
or open *$sym, ">&=$_[0]" # or this |
| 371 |
or return undef; |
| 372 |
|
| 373 |
*$sym |
| 374 |
} |
| 375 |
|
| 376 |
min_parallel 4; |
| 377 |
|
| 378 |
END { |
| 379 |
max_parallel 0; |
| 380 |
} |
| 381 |
|
| 382 |
1; |
| 383 |
|
| 384 |
=head2 FORK BEHAVIOUR |
| 385 |
|
| 386 |
Before the fork, IO::AIO enters a quiescent state where no requests |
| 387 |
can be added in other threads and no results will be processed. After |
| 388 |
the fork the parent simply leaves the quiescent state and continues |
| 389 |
request/result processing, while the child clears the request/result |
| 390 |
queue (so the requests started before the fork will only be handled in |
| 391 |
the parent). Threats will be started on demand until the limit ste in the |
| 392 |
parent process has been reached again. |
| 393 |
|
| 394 |
=head1 SEE ALSO |
| 395 |
|
| 396 |
L<Coro>, L<Linux::AIO>. |
| 397 |
|
| 398 |
=head1 AUTHOR |
| 399 |
|
| 400 |
Marc Lehmann <schmorp@schmorp.de> |
| 401 |
http://home.schmorp.de/ |
| 402 |
|
| 403 |
=cut |
| 404 |
|
