| … | |
… | |
| 168 | aio_unlink $pathname, $callback->($status) |
168 | aio_unlink $pathname, $callback->($status) |
| 169 | aio_mknod $path, $mode, $dev, $callback->($status) |
169 | aio_mknod $path, $mode, $dev, $callback->($status) |
| 170 | aio_link $srcpath, $dstpath, $callback->($status) |
170 | aio_link $srcpath, $dstpath, $callback->($status) |
| 171 | aio_symlink $srcpath, $dstpath, $callback->($status) |
171 | aio_symlink $srcpath, $dstpath, $callback->($status) |
| 172 | aio_readlink $path, $callback->($link) |
172 | aio_readlink $path, $callback->($link) |
|
|
173 | aio_realpath $path, $callback->($link) |
| 173 | aio_rename $srcpath, $dstpath, $callback->($status) |
174 | aio_rename $srcpath, $dstpath, $callback->($status) |
| 174 | aio_mkdir $pathname, $mode, $callback->($status) |
175 | aio_mkdir $pathname, $mode, $callback->($status) |
| 175 | aio_rmdir $pathname, $callback->($status) |
176 | aio_rmdir $pathname, $callback->($status) |
| 176 | aio_readdir $pathname, $callback->($entries) |
177 | aio_readdir $pathname, $callback->($entries) |
| 177 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
178 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
| … | |
… | |
| 306 | } else { |
307 | } else { |
| 307 | die "open failed: $!\n"; |
308 | die "open failed: $!\n"; |
| 308 | } |
309 | } |
| 309 | }; |
310 | }; |
| 310 | |
311 | |
|
|
312 | In addition to all the common open modes/flags ("O_RDONLY", |
|
|
313 | "O_WRONLY", "O_RDWR", "O_CREAT", "O_TRUNC", "O_EXCL" and |
|
|
314 | "O_APPEND"), the following POSIX and non-POSIX constants are |
|
|
315 | available (missing ones on your system are, as usual, 0): |
|
|
316 | |
|
|
317 | "O_ASYNC", "O_DIRECT", "O_NOATIME", "O_CLOEXEC", "O_NOCTTY", |
|
|
318 | "O_NOFOLLOW", "O_NONBLOCK", "O_EXEC", "O_SEARCH", "O_DIRECTORY", |
|
|
319 | "O_DSYNC", "O_RSYNC", "O_SYNC" and "O_TTY_INIT". |
|
|
320 | |
| 311 | aio_close $fh, $callback->($status) |
321 | aio_close $fh, $callback->($status) |
| 312 | Asynchronously close a file and call the callback with the result |
322 | Asynchronously close a file and call the callback with the result |
| 313 | code. |
323 | code. |
| 314 | |
324 | |
| 315 | Unfortunately, you can't do this to perl. Perl *insists* very |
325 | Unfortunately, you can't do this to perl. Perl *insists* very |
| … | |
… | |
| 358 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
368 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
| 359 | Tries to copy $length bytes from $in_fh to $out_fh. It starts |
369 | Tries to copy $length bytes from $in_fh to $out_fh. It starts |
| 360 | reading at byte offset $in_offset, and starts writing at the current |
370 | reading at byte offset $in_offset, and starts writing at the current |
| 361 | file offset of $out_fh. Because of that, it is not safe to issue |
371 | file offset of $out_fh. Because of that, it is not safe to issue |
| 362 | more than one "aio_sendfile" per $out_fh, as they will interfere |
372 | more than one "aio_sendfile" per $out_fh, as they will interfere |
| 363 | with each other. |
373 | with each other. The same $in_fh works fine though, as this function |
|
|
374 | does not move or use the file offset of $in_fh. |
| 364 | |
375 | |
| 365 | Please note that "aio_sendfile" can read more bytes from $in_fh than |
376 | Please note that "aio_sendfile" can read more bytes from $in_fh than |
| 366 | are written, and there is no way to find out how many bytes have |
377 | are written, and there is no way to find out how many more bytes |
| 367 | been read from "aio_sendfile" alone, as "aio_sendfile" only provides |
378 | have been read from "aio_sendfile" alone, as "aio_sendfile" only |
| 368 | the number of bytes written to $out_fh. Only if the result value |
379 | provides the number of bytes written to $out_fh. Only if the result |
| 369 | equals $length one can assume that $length bytes have been read. |
380 | value equals $length one can assume that $length bytes have been |
|
|
381 | read. |
| 370 | |
382 | |
| 371 | Unlike with other "aio_" functions, it makes a lot of sense to use |
383 | Unlike with other "aio_" functions, it makes a lot of sense to use |
| 372 | "aio_sendfile" on non-blocking sockets, as long as one end |
384 | "aio_sendfile" on non-blocking sockets, as long as one end |
| 373 | (typically the $in_fh) is a file - the file I/O will then be |
385 | (typically the $in_fh) is a file - the file I/O will then be |
| 374 | asynchronous, while the socket I/O will be non-blocking. Note, |
386 | asynchronous, while the socket I/O will be non-blocking. Note, |
| 375 | however, that you can run into a trap where "aio_sendfile" reads |
387 | however, that you can run into a trap where "aio_sendfile" reads |
| 376 | some data with readahead, then fails to write all data, and when the |
388 | some data with readahead, then fails to write all data, and when the |
| 377 | socket is ready the next time, the data in the cache is already |
389 | socket is ready the next time, the data in the cache is already |
| 378 | lost, forcing "aio_sendfile" to again hit the disk. Explicit |
390 | lost, forcing "aio_sendfile" to again hit the disk. Explicit |
| 379 | "aio_read" + "aio_write" let's you control resource usage much |
391 | "aio_read" + "aio_write" let's you better control resource usage. |
| 380 | better. |
|
|
| 381 | |
392 | |
| 382 | This call tries to make use of a native "sendfile" syscall to |
393 | This call tries to make use of a native "sendfile"-like syscall to |
| 383 | provide zero-copy operation. For this to work, $out_fh should refer |
394 | provide zero-copy operation. For this to work, $out_fh should refer |
| 384 | to a socket, and $in_fh should refer to an mmap'able file. |
395 | to a socket, and $in_fh should refer to an mmap'able file. |
| 385 | |
396 | |
| 386 | If a native sendfile cannot be found or it fails with "ENOSYS", |
397 | If a native sendfile cannot be found or it fails with "ENOSYS", |
| 387 | "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK", |
398 | "EINVAL", "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or |
| 388 | it will be emulated, so you can call "aio_sendfile" on any type of |
399 | "ENOTSOCK", it will be emulated, so you can call "aio_sendfile" on |
| 389 | filehandle regardless of the limitations of the operating system. |
400 | any type of filehandle regardless of the limitations of the |
|
|
401 | operating system. |
|
|
402 | |
|
|
403 | As native sendfile syscalls (as practically any non-POSIX interface |
|
|
404 | hacked together in a hurry to improve benchmark numbers) tend to be |
|
|
405 | rather buggy on many systems, this implementation tries to work |
|
|
406 | around some known bugs in Linux and FreeBSD kernels (probably |
|
|
407 | others, too), but that might fail, so you really really should check |
|
|
408 | the return value of "aio_sendfile" - fewre bytes than expected might |
|
|
409 | have been transferred. |
| 390 | |
410 | |
| 391 | aio_readahead $fh,$offset,$length, $callback->($retval) |
411 | aio_readahead $fh,$offset,$length, $callback->($retval) |
| 392 | "aio_readahead" populates the page cache with data from a file so |
412 | "aio_readahead" populates the page cache with data from a file so |
| 393 | that subsequent reads from that file will not block on disk I/O. The |
413 | that subsequent reads from that file will not block on disk I/O. The |
| 394 | $offset argument specifies the starting point from which data is to |
414 | $offset argument specifies the starting point from which data is to |
| … | |
… | |
| 538 | aio_readlink $path, $callback->($link) |
558 | aio_readlink $path, $callback->($link) |
| 539 | Asynchronously read the symlink specified by $path and pass it to |
559 | Asynchronously read the symlink specified by $path and pass it to |
| 540 | the callback. If an error occurs, nothing or undef gets passed to |
560 | the callback. If an error occurs, nothing or undef gets passed to |
| 541 | the callback. |
561 | the callback. |
| 542 | |
562 | |
|
|
563 | aio_realpath $path, $callback->($path) |
|
|
564 | Asynchronously make the path absolute and resolve any symlinks in |
|
|
565 | $path. The resulting path only consists of directories (Same as |
|
|
566 | Cwd::realpath). |
|
|
567 | |
|
|
568 | This request can be used to get the absolute path of the current |
|
|
569 | working directory by passing it a path of . (a single dot). |
|
|
570 | |
| 543 | aio_rename $srcpath, $dstpath, $callback->($status) |
571 | aio_rename $srcpath, $dstpath, $callback->($status) |
| 544 | Asynchronously rename the object at $srcpath to $dstpath, just as |
572 | Asynchronously rename the object at $srcpath to $dstpath, just as |
| 545 | rename(2) and call the callback with the result code. |
573 | rename(2) and call the callback with the result code. |
| 546 | |
574 | |
| 547 | aio_mkdir $pathname, $mode, $callback->($status) |
575 | aio_mkdir $pathname, $mode, $callback->($status) |
| … | |
… | |
| 569 | The flags are a combination of the following constants, ORed |
597 | The flags are a combination of the following constants, ORed |
| 570 | together (the flags will also be passed to the callback, possibly |
598 | together (the flags will also be passed to the callback, possibly |
| 571 | modified): |
599 | modified): |
| 572 | |
600 | |
| 573 | IO::AIO::READDIR_DENTS |
601 | IO::AIO::READDIR_DENTS |
| 574 | When this flag is off, then the callback gets an arrayref with |
602 | When this flag is off, then the callback gets an arrayref |
| 575 | of names only (as with "aio_readdir"), otherwise it gets an |
603 | consisting of names only (as with "aio_readdir"), otherwise it |
| 576 | arrayref with "[$name, $type, $inode]" arrayrefs, each |
604 | gets an arrayref with "[$name, $type, $inode]" arrayrefs, each |
| 577 | describing a single directory entry in more detail. |
605 | describing a single directory entry in more detail. |
| 578 | |
606 | |
| 579 | $name is the name of the entry. |
607 | $name is the name of the entry. |
| 580 | |
608 | |
| 581 | $type is one of the "IO::AIO::DT_xxx" constants: |
609 | $type is one of the "IO::AIO::DT_xxx" constants: |
| … | |
… | |
| 594 | unspecified content on systems that do not deliver the inode |
622 | unspecified content on systems that do not deliver the inode |
| 595 | information. |
623 | information. |
| 596 | |
624 | |
| 597 | IO::AIO::READDIR_DIRS_FIRST |
625 | IO::AIO::READDIR_DIRS_FIRST |
| 598 | When this flag is set, then the names will be returned in an |
626 | When this flag is set, then the names will be returned in an |
| 599 | order where likely directories come first. This is useful when |
627 | order where likely directories come first, in optimal stat |
| 600 | you need to quickly find directories, or you want to find all |
628 | order. This is useful when you need to quickly find directories, |
| 601 | directories while avoiding to stat() each entry. |
629 | or you want to find all directories while avoiding to stat() |
|
|
630 | each entry. |
| 602 | |
631 | |
| 603 | If the system returns type information in readdir, then this is |
632 | If the system returns type information in readdir, then this is |
| 604 | used to find directories directly. Otherwise, likely directories |
633 | used to find directories directly. Otherwise, likely directories |
| 605 | are files beginning with ".", or otherwise files with no dots, |
634 | are names beginning with ".", or otherwise names with no dots, |
| 606 | of which files with short names are tried first. |
635 | of which names with short names are tried first. |
| 607 | |
636 | |
| 608 | IO::AIO::READDIR_STAT_ORDER |
637 | IO::AIO::READDIR_STAT_ORDER |
| 609 | When this flag is set, then the names will be returned in an |
638 | When this flag is set, then the names will be returned in an |
| 610 | order suitable for stat()'ing each one. That is, when you plan |
639 | order suitable for stat()'ing each one. That is, when you plan |
| 611 | to stat() all files in the given directory, then the returned |
640 | to stat() all files in the given directory, then the returned |
| … | |
… | |
| 1022 | |
1051 | |
| 1023 | See "poll_cb" for an example. |
1052 | See "poll_cb" for an example. |
| 1024 | |
1053 | |
| 1025 | IO::AIO::poll_cb |
1054 | IO::AIO::poll_cb |
| 1026 | Process some outstanding events on the result pipe. You have to call |
1055 | Process some outstanding events on the result pipe. You have to call |
| 1027 | this regularly. Returns 0 if all events could be processed, or -1 if |
1056 | this regularly. Returns 0 if all events could be processed (or there |
| 1028 | it returned earlier for whatever reason. Returns immediately when no |
1057 | were no events to process), or -1 if it returned earlier for |
| 1029 | events are outstanding. The amount of events processed depends on |
1058 | whatever reason. Returns immediately when no events are outstanding. |
| 1030 | the settings of "IO::AIO::max_poll_req" and |
1059 | The amount of events processed depends on the settings of |
| 1031 | "IO::AIO::max_poll_time". |
1060 | "IO::AIO::max_poll_req" and "IO::AIO::max_poll_time". |
| 1032 | |
1061 | |
| 1033 | If not all requests were processed for whatever reason, the |
1062 | If not all requests were processed for whatever reason, the |
| 1034 | filehandle will still be ready when "poll_cb" returns, so normally |
1063 | filehandle will still be ready when "poll_cb" returns, so normally |
| 1035 | you don't have to do anything special to have it called later. |
1064 | you don't have to do anything special to have it called later. |
|
|
1065 | |
|
|
1066 | Apart from calling "IO::AIO::poll_cb" when the event filehandle |
|
|
1067 | becomes ready, it can be beneficial to call this function from loops |
|
|
1068 | which submit a lot of requests, to make sure the results get |
|
|
1069 | processed when they become available and not just when the loop is |
|
|
1070 | finished and the event loop takes over again. This function returns |
|
|
1071 | very fast when there are no outstanding requests. |
| 1036 | |
1072 | |
| 1037 | Example: Install an Event watcher that automatically calls |
1073 | Example: Install an Event watcher that automatically calls |
| 1038 | IO::AIO::poll_cb with high priority (more examples can be found in |
1074 | IO::AIO::poll_cb with high priority (more examples can be found in |
| 1039 | the SYNOPSIS section, at the top of this document): |
1075 | the SYNOPSIS section, at the top of this document): |
| 1040 | |
1076 | |
| … | |
… | |
| 1153 | IO::AIO::idle_timeout $seconds |
1189 | IO::AIO::idle_timeout $seconds |
| 1154 | Sets the minimum idle timeout (default 10) after which worker |
1190 | Sets the minimum idle timeout (default 10) after which worker |
| 1155 | threads are allowed to exit. SEe "IO::AIO::max_idle". |
1191 | threads are allowed to exit. SEe "IO::AIO::max_idle". |
| 1156 | |
1192 | |
| 1157 | IO::AIO::max_outstanding $maxreqs |
1193 | IO::AIO::max_outstanding $maxreqs |
|
|
1194 | Sets the maximum number of outstanding requests to $nreqs. If you do |
|
|
1195 | queue up more than this number of requests, the next call to |
|
|
1196 | "IO::AIO::poll_cb" (and other functions calling "poll_cb", such as |
|
|
1197 | "IO::AIO::flush" or "IO::AIO::poll") will block until the limit is |
|
|
1198 | no longer exceeded. |
|
|
1199 | |
|
|
1200 | In other words, this setting does not enforce a queue limit, but can |
|
|
1201 | be used to make poll functions block if the limit is exceeded. |
|
|
1202 | |
| 1158 | This is a very bad function to use in interactive programs because |
1203 | This is a very bad function to use in interactive programs because |
| 1159 | it blocks, and a bad way to reduce concurrency because it is |
1204 | it blocks, and a bad way to reduce concurrency because it is |
| 1160 | inexact: Better use an "aio_group" together with a feed callback. |
1205 | inexact: Better use an "aio_group" together with a feed callback. |
| 1161 | |
1206 | |
| 1162 | Sets the maximum number of outstanding requests to $nreqs. If you do |
1207 | It's main use is in scripts without an event loop - when you want to |
| 1163 | queue up more than this number of requests, the next call to the |
1208 | stat a lot of files, you can write somehting like this: |
| 1164 | "poll_cb" (and "poll_some" and other functions calling "poll_cb") |
|
|
| 1165 | function will block until the limit is no longer exceeded. |
|
|
| 1166 | |
1209 | |
| 1167 | The default value is very large, so there is no practical limit on |
1210 | IO::AIO::max_outstanding 32; |
|
|
1211 | |
|
|
1212 | for my $path (...) { |
|
|
1213 | aio_stat $path , ...; |
|
|
1214 | IO::AIO::poll_cb; |
|
|
1215 | } |
|
|
1216 | |
|
|
1217 | IO::AIO::flush; |
|
|
1218 | |
|
|
1219 | The call to "poll_cb" inside the loop will normally return |
|
|
1220 | instantly, but as soon as more thna 32 reqeusts are in-flight, it |
|
|
1221 | will block until some requests have been handled. This keeps the |
|
|
1222 | loop from pushing a large number of "aio_stat" requests onto the |
|
|
1223 | queue. |
|
|
1224 | |
|
|
1225 | The default value for "max_outstanding" is very large, so there is |
| 1168 | the number of outstanding requests. |
1226 | no practical limit on the number of outstanding requests. |
| 1169 | |
|
|
| 1170 | You can still queue as many requests as you want. Therefore, |
|
|
| 1171 | "max_outstanding" is mainly useful in simple scripts (with low |
|
|
| 1172 | values) or as a stop gap to shield against fatal memory overflow |
|
|
| 1173 | (with large values). |
|
|
| 1174 | |
1227 | |
| 1175 | STATISTICAL INFORMATION |
1228 | STATISTICAL INFORMATION |
| 1176 | IO::AIO::nreqs |
1229 | IO::AIO::nreqs |
| 1177 | Returns the number of requests currently in the ready, execute or |
1230 | Returns the number of requests currently in the ready, execute or |
| 1178 | pending states (i.e. for which their callback has not been invoked |
1231 | pending states (i.e. for which their callback has not been invoked |
| … | |
… | |
| 1324 | # Danga::Socket integration |
1377 | # Danga::Socket integration |
| 1325 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
1378 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
| 1326 | \&IO::AIO::poll_cb); |
1379 | \&IO::AIO::poll_cb); |
| 1327 | |
1380 | |
| 1328 | FORK BEHAVIOUR |
1381 | FORK BEHAVIOUR |
| 1329 | This module should do "the right thing" when the process using it forks: |
1382 | Usage of pthreads in a program changes the semantics of fork |
|
|
1383 | considerably. Specifically, only async-safe functions can be called |
|
|
1384 | after fork. Perl doesn't know about this, so in general, you cannot call |
|
|
1385 | fork with defined behaviour in perl if pthreads are involved. IO::AIO |
|
|
1386 | uses pthreads, so this applies, but many other extensions and (for |
|
|
1387 | inexplicable reasons) perl itself often is linked against pthreads, so |
|
|
1388 | this limitation applies to quite a lot of perls. |
| 1330 | |
1389 | |
| 1331 | Before the fork, IO::AIO enters a quiescent state where no requests can |
1390 | This module no longer tries to fight your OS, or POSIX. That means |
| 1332 | be added in other threads and no results will be processed. After the |
1391 | IO::AIO only works in the process that loaded it. Forking is fully |
| 1333 | fork the parent simply leaves the quiescent state and continues |
1392 | supported, but using IO::AIO in the child is not. |
| 1334 | request/result processing, while the child frees the request/result |
|
|
| 1335 | queue (so that the requests started before the fork will only be handled |
|
|
| 1336 | in the parent). Threads will be started on demand until the limit set in |
|
|
| 1337 | the parent process has been reached again. |
|
|
| 1338 | |
1393 | |
| 1339 | In short: the parent will, after a short pause, continue as if fork had |
1394 | You might get around by not *using* IO::AIO before (or after) forking. |
| 1340 | not been called, while the child will act as if IO::AIO has not been |
1395 | You could also try to call the IO::AIO::reinit function in the child: |
| 1341 | used yet. |
1396 | |
|
|
1397 | IO::AIO::reinit |
|
|
1398 | Abondons all current requests and I/O threads and simply |
|
|
1399 | reinitialises all data structures. This is not an operation |
|
|
1400 | suppported by any standards, but happens to work on GNU/Linux and |
|
|
1401 | some newer BSD systems. |
|
|
1402 | |
|
|
1403 | The only reasonable use for this function is to call it after |
|
|
1404 | forking, if "IO::AIO" was used in the parent. Calling it while |
|
|
1405 | IO::AIO is active in the process will result in undefined behaviour. |
|
|
1406 | Calling it at any time will also result in any undefined (by POSIX) |
|
|
1407 | behaviour. |
| 1342 | |
1408 | |
| 1343 | MEMORY USAGE |
1409 | MEMORY USAGE |
| 1344 | Per-request usage: |
1410 | Per-request usage: |
| 1345 | |
1411 | |
| 1346 | Each aio request uses - depending on your architecture - around 100-200 |
1412 | Each aio request uses - depending on your architecture - around 100-200 |
