… | |
… | |
168 | use common::sense; |
168 | use common::sense; |
169 | |
169 | |
170 | use base 'Exporter'; |
170 | use base 'Exporter'; |
171 | |
171 | |
172 | BEGIN { |
172 | BEGIN { |
173 | our $VERSION = '3.72'; |
173 | our $VERSION = '3.93'; |
174 | |
174 | |
175 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
175 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
176 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
176 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
177 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
177 | aio_scandir aio_symlink aio_readlink aio_realpath aio_sync aio_fsync |
178 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
178 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
179 | aio_rename aio_link aio_move aio_copy aio_group |
179 | aio_rename aio_link aio_move aio_copy aio_group |
180 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
180 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
181 | aio_chmod aio_utime aio_truncate |
181 | aio_chmod aio_utime aio_truncate |
182 | aio_msync aio_mtouch aio_mlock aio_mlockall |
182 | aio_msync aio_mtouch aio_mlock aio_mlockall |
… | |
… | |
222 | aio_unlink $pathname, $callback->($status) |
222 | aio_unlink $pathname, $callback->($status) |
223 | aio_mknod $path, $mode, $dev, $callback->($status) |
223 | aio_mknod $path, $mode, $dev, $callback->($status) |
224 | aio_link $srcpath, $dstpath, $callback->($status) |
224 | aio_link $srcpath, $dstpath, $callback->($status) |
225 | aio_symlink $srcpath, $dstpath, $callback->($status) |
225 | aio_symlink $srcpath, $dstpath, $callback->($status) |
226 | aio_readlink $path, $callback->($link) |
226 | aio_readlink $path, $callback->($link) |
|
|
227 | aio_realpath $path, $callback->($link) |
227 | aio_rename $srcpath, $dstpath, $callback->($status) |
228 | aio_rename $srcpath, $dstpath, $callback->($status) |
228 | aio_mkdir $pathname, $mode, $callback->($status) |
229 | aio_mkdir $pathname, $mode, $callback->($status) |
229 | aio_rmdir $pathname, $callback->($status) |
230 | aio_rmdir $pathname, $callback->($status) |
230 | aio_readdir $pathname, $callback->($entries) |
231 | aio_readdir $pathname, $callback->($entries) |
231 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
232 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
… | |
… | |
368 | } else { |
369 | } else { |
369 | die "open failed: $!\n"; |
370 | die "open failed: $!\n"; |
370 | } |
371 | } |
371 | }; |
372 | }; |
372 | |
373 | |
|
|
374 | In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>, |
|
|
375 | C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the |
|
|
376 | following POSIX and non-POSIX constants are available (missing ones on |
|
|
377 | your system are, as usual, C<0>): |
|
|
378 | |
|
|
379 | C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>, |
|
|
380 | C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>, |
|
|
381 | C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>. |
|
|
382 | |
373 | |
383 | |
374 | =item aio_close $fh, $callback->($status) |
384 | =item aio_close $fh, $callback->($status) |
375 | |
385 | |
376 | Asynchronously close a file and call the callback with the result |
386 | Asynchronously close a file and call the callback with the result |
377 | code. |
387 | code. |
… | |
… | |
427 | |
437 | |
428 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
438 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
429 | reading at byte offset C<$in_offset>, and starts writing at the current |
439 | reading at byte offset C<$in_offset>, and starts writing at the current |
430 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
440 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
431 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
441 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
432 | other. |
442 | other. The same C<$in_fh> works fine though, as this function does not |
|
|
443 | move or use the file offset of C<$in_fh>. |
433 | |
444 | |
434 | Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than |
445 | Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than |
435 | are written, and there is no way to find out how many bytes have been read |
446 | are written, and there is no way to find out how many more bytes have been |
436 | from C<aio_sendfile> alone, as C<aio_sendfile> only provides the number of |
447 | read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the |
437 | bytes written to C<$out_fh>. Only if the result value equals C<$length> |
448 | number of bytes written to C<$out_fh>. Only if the result value equals |
438 | one can assume that C<$length> bytes have been read. |
449 | C<$length> one can assume that C<$length> bytes have been read. |
439 | |
450 | |
440 | Unlike with other C<aio_> functions, it makes a lot of sense to use |
451 | Unlike with other C<aio_> functions, it makes a lot of sense to use |
441 | C<aio_sendfile> on non-blocking sockets, as long as one end (typically |
452 | C<aio_sendfile> on non-blocking sockets, as long as one end (typically |
442 | the C<$in_fh>) is a file - the file I/O will then be asynchronous, while |
453 | the C<$in_fh>) is a file - the file I/O will then be asynchronous, while |
443 | the socket I/O will be non-blocking. Note, however, that you can run into |
454 | the socket I/O will be non-blocking. Note, however, that you can run |
444 | a trap where C<aio_sendfile> reads some data with readahead, then fails |
455 | into a trap where C<aio_sendfile> reads some data with readahead, then |
445 | to write all data, and when the socket is ready the next time, the data |
456 | fails to write all data, and when the socket is ready the next time, the |
446 | in the cache is already lost, forcing C<aio_sendfile> to again hit the |
457 | data in the cache is already lost, forcing C<aio_sendfile> to again hit |
447 | disk. Explicit C<aio_read> + C<aio_write> let's you control resource usage |
458 | the disk. Explicit C<aio_read> + C<aio_write> let's you better control |
448 | much better. |
459 | resource usage. |
449 | |
460 | |
450 | This call tries to make use of a native C<sendfile> syscall to provide |
461 | This call tries to make use of a native C<sendfile>-like syscall to |
451 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
462 | provide zero-copy operation. For this to work, C<$out_fh> should refer to |
452 | socket, and C<$in_fh> should refer to an mmap'able file. |
463 | a socket, and C<$in_fh> should refer to an mmap'able file. |
453 | |
464 | |
454 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
465 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
455 | C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or C<ENOTSOCK>, |
466 | C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or |
456 | it will be emulated, so you can call C<aio_sendfile> on any type of |
467 | C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any |
457 | filehandle regardless of the limitations of the operating system. |
468 | type of filehandle regardless of the limitations of the operating system. |
|
|
469 | |
|
|
470 | As native sendfile syscalls (as practically any non-POSIX interface hacked |
|
|
471 | together in a hurry to improve benchmark numbers) tend to be rather buggy |
|
|
472 | on many systems, this implementation tries to work around some known bugs |
|
|
473 | in Linux and FreeBSD kernels (probably others, too), but that might fail, |
|
|
474 | so you really really should check the return value of C<aio_sendfile> - |
|
|
475 | fewre bytes than expected might have been transferred. |
458 | |
476 | |
459 | |
477 | |
460 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
478 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
461 | |
479 | |
462 | C<aio_readahead> populates the page cache with data from a file so that |
480 | C<aio_readahead> populates the page cache with data from a file so that |
… | |
… | |
626 | Asynchronously read the symlink specified by C<$path> and pass it to |
644 | Asynchronously read the symlink specified by C<$path> and pass it to |
627 | the callback. If an error occurs, nothing or undef gets passed to the |
645 | the callback. If an error occurs, nothing or undef gets passed to the |
628 | callback. |
646 | callback. |
629 | |
647 | |
630 | |
648 | |
|
|
649 | =item aio_realpath $path, $callback->($path) |
|
|
650 | |
|
|
651 | Asynchronously make the path absolute and resolve any symlinks in |
|
|
652 | C<$path>. The resulting path only consists of directories. |
|
|
653 | |
|
|
654 | This request can be used to get the absolute path of the current working |
|
|
655 | directory by passing it a path of F<.> (a single dot). |
|
|
656 | |
|
|
657 | |
631 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
658 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
632 | |
659 | |
633 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
660 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
634 | rename(2) and call the callback with the result code. |
661 | rename(2) and call the callback with the result code. |
635 | |
662 | |
… | |
… | |
668 | |
695 | |
669 | =over 4 |
696 | =over 4 |
670 | |
697 | |
671 | =item IO::AIO::READDIR_DENTS |
698 | =item IO::AIO::READDIR_DENTS |
672 | |
699 | |
673 | When this flag is off, then the callback gets an arrayref with of names |
700 | When this flag is off, then the callback gets an arrayref consisting of |
674 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
701 | names only (as with C<aio_readdir>), otherwise it gets an arrayref with |
675 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
702 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
676 | entry in more detail. |
703 | entry in more detail. |
677 | |
704 | |
678 | C<$name> is the name of the entry. |
705 | C<$name> is the name of the entry. |
679 | |
706 | |
… | |
… | |
692 | systems that do not deliver the inode information. |
719 | systems that do not deliver the inode information. |
693 | |
720 | |
694 | =item IO::AIO::READDIR_DIRS_FIRST |
721 | =item IO::AIO::READDIR_DIRS_FIRST |
695 | |
722 | |
696 | When this flag is set, then the names will be returned in an order where |
723 | When this flag is set, then the names will be returned in an order where |
697 | likely directories come first. This is useful when you need to quickly |
724 | likely directories come first, in optimal stat order. This is useful when |
698 | find directories, or you want to find all directories while avoiding to |
725 | you need to quickly find directories, or you want to find all directories |
699 | stat() each entry. |
726 | while avoiding to stat() each entry. |
700 | |
727 | |
701 | If the system returns type information in readdir, then this is used |
728 | If the system returns type information in readdir, then this is used |
702 | to find directories directly. Otherwise, likely directories are files |
729 | to find directories directly. Otherwise, likely directories are names |
703 | beginning with ".", or otherwise files with no dots, of which files with |
730 | beginning with ".", or otherwise names with no dots, of which names with |
704 | short names are tried first. |
731 | short names are tried first. |
705 | |
732 | |
706 | =item IO::AIO::READDIR_STAT_ORDER |
733 | =item IO::AIO::READDIR_STAT_ORDER |
707 | |
734 | |
708 | When this flag is set, then the names will be returned in an order |
735 | When this flag is set, then the names will be returned in an order |
… | |
… | |
853 | if ($_[0] && $! == EXDEV) { |
880 | if ($_[0] && $! == EXDEV) { |
854 | aioreq_pri $pri; |
881 | aioreq_pri $pri; |
855 | add $grp aio_copy $src, $dst, sub { |
882 | add $grp aio_copy $src, $dst, sub { |
856 | $grp->result ($_[0]); |
883 | $grp->result ($_[0]); |
857 | |
884 | |
858 | if (!$_[0]) { |
885 | unless ($_[0]) { |
859 | aioreq_pri $pri; |
886 | aioreq_pri $pri; |
860 | add $grp aio_unlink $src; |
887 | add $grp aio_unlink $src; |
861 | } |
888 | } |
862 | }; |
889 | }; |
863 | } else { |
890 | } else { |
… | |
… | |
1406 | |
1433 | |
1407 | See C<poll_cb> for an example. |
1434 | See C<poll_cb> for an example. |
1408 | |
1435 | |
1409 | =item IO::AIO::poll_cb |
1436 | =item IO::AIO::poll_cb |
1410 | |
1437 | |
1411 | Process some outstanding events on the result pipe. You have to call this |
1438 | Process some outstanding events on the result pipe. You have to call |
1412 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
1439 | this regularly. Returns C<0> if all events could be processed (or there |
1413 | returned earlier for whatever reason. Returns immediately when no events |
1440 | were no events to process), or C<-1> if it returned earlier for whatever |
1414 | are outstanding. The amount of events processed depends on the settings of |
1441 | reason. Returns immediately when no events are outstanding. The amount of |
1415 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
1442 | events processed depends on the settings of C<IO::AIO::max_poll_req> and |
|
|
1443 | C<IO::AIO::max_poll_time>. |
1416 | |
1444 | |
1417 | If not all requests were processed for whatever reason, the filehandle |
1445 | If not all requests were processed for whatever reason, the filehandle |
1418 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1446 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1419 | do anything special to have it called later. |
1447 | do anything special to have it called later. |
|
|
1448 | |
|
|
1449 | Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes |
|
|
1450 | ready, it can be beneficial to call this function from loops which submit |
|
|
1451 | a lot of requests, to make sure the results get processed when they become |
|
|
1452 | available and not just when the loop is finished and the event loop takes |
|
|
1453 | over again. This function returns very fast when there are no outstanding |
|
|
1454 | requests. |
1420 | |
1455 | |
1421 | Example: Install an Event watcher that automatically calls |
1456 | Example: Install an Event watcher that automatically calls |
1422 | IO::AIO::poll_cb with high priority (more examples can be found in the |
1457 | IO::AIO::poll_cb with high priority (more examples can be found in the |
1423 | SYNOPSIS section, at the top of this document): |
1458 | SYNOPSIS section, at the top of this document): |
1424 | |
1459 | |
… | |
… | |
1547 | Sets the minimum idle timeout (default 10) after which worker threads are |
1582 | Sets the minimum idle timeout (default 10) after which worker threads are |
1548 | allowed to exit. SEe C<IO::AIO::max_idle>. |
1583 | allowed to exit. SEe C<IO::AIO::max_idle>. |
1549 | |
1584 | |
1550 | =item IO::AIO::max_outstanding $maxreqs |
1585 | =item IO::AIO::max_outstanding $maxreqs |
1551 | |
1586 | |
|
|
1587 | Sets the maximum number of outstanding requests to C<$nreqs>. If |
|
|
1588 | you do queue up more than this number of requests, the next call to |
|
|
1589 | C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as |
|
|
1590 | C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no |
|
|
1591 | longer exceeded. |
|
|
1592 | |
|
|
1593 | In other words, this setting does not enforce a queue limit, but can be |
|
|
1594 | used to make poll functions block if the limit is exceeded. |
|
|
1595 | |
1552 | This is a very bad function to use in interactive programs because it |
1596 | This is a very bad function to use in interactive programs because it |
1553 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1597 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1554 | use an C<aio_group> together with a feed callback. |
1598 | use an C<aio_group> together with a feed callback. |
1555 | |
1599 | |
1556 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1600 | It's main use is in scripts without an event loop - when you want to stat |
1557 | do queue up more than this number of requests, the next call to the |
1601 | a lot of files, you can write somehting like this: |
1558 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1559 | function will block until the limit is no longer exceeded. |
|
|
1560 | |
1602 | |
1561 | The default value is very large, so there is no practical limit on the |
1603 | IO::AIO::max_outstanding 32; |
1562 | number of outstanding requests. |
|
|
1563 | |
1604 | |
1564 | You can still queue as many requests as you want. Therefore, |
1605 | for my $path (...) { |
1565 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
1606 | aio_stat $path , ...; |
1566 | as a stop gap to shield against fatal memory overflow (with large values). |
1607 | IO::AIO::poll_cb; |
|
|
1608 | } |
|
|
1609 | |
|
|
1610 | IO::AIO::flush; |
|
|
1611 | |
|
|
1612 | The call to C<poll_cb> inside the loop will normally return instantly, but |
|
|
1613 | as soon as more thna C<32> reqeusts are in-flight, it will block until |
|
|
1614 | some requests have been handled. This keeps the loop from pushing a large |
|
|
1615 | number of C<aio_stat> requests onto the queue. |
|
|
1616 | |
|
|
1617 | The default value for C<max_outstanding> is very large, so there is no |
|
|
1618 | practical limit on the number of outstanding requests. |
1567 | |
1619 | |
1568 | =back |
1620 | =back |
1569 | |
1621 | |
1570 | =head3 STATISTICAL INFORMATION |
1622 | =head3 STATISTICAL INFORMATION |
1571 | |
1623 | |
… | |
… | |
1747 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
1799 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
1748 | \&IO::AIO::poll_cb); |
1800 | \&IO::AIO::poll_cb); |
1749 | |
1801 | |
1750 | =head2 FORK BEHAVIOUR |
1802 | =head2 FORK BEHAVIOUR |
1751 | |
1803 | |
1752 | This module should do "the right thing" when the process using it forks: |
1804 | Usage of pthreads in a program changes the semantics of fork |
|
|
1805 | considerably. Specifically, only async-safe functions can be called after |
|
|
1806 | fork. Perl doesn't know about this, so in general, you cannot call fork |
|
|
1807 | with defined behaviour in perl. IO::AIO uses pthreads, so this applies, |
|
|
1808 | but many other extensions and (for inexplicable reasons) perl itself often |
|
|
1809 | is linked against pthreads, so this limitation applies. |
1753 | |
1810 | |
1754 | Before the fork, IO::AIO enters a quiescent state where no requests |
1811 | Some operating systems have extensions that allow safe use of fork, and |
1755 | can be added in other threads and no results will be processed. After |
1812 | this module should do "the right thing" on those, and tries on others. At |
1756 | the fork the parent simply leaves the quiescent state and continues |
1813 | the time of this writing (2011) only GNU/Linux supports these extensions |
1757 | request/result processing, while the child frees the request/result queue |
1814 | to POSIX. |
1758 | (so that the requests started before the fork will only be handled in the |
|
|
1759 | parent). Threads will be started on demand until the limit set in the |
|
|
1760 | parent process has been reached again. |
|
|
1761 | |
|
|
1762 | In short: the parent will, after a short pause, continue as if fork had |
|
|
1763 | not been called, while the child will act as if IO::AIO has not been used |
|
|
1764 | yet. |
|
|
1765 | |
1815 | |
1766 | =head2 MEMORY USAGE |
1816 | =head2 MEMORY USAGE |
1767 | |
1817 | |
1768 | Per-request usage: |
1818 | Per-request usage: |
1769 | |
1819 | |