… | |
… | |
30 | |
30 | |
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
32 | use AnyEvent::AIO; |
32 | use AnyEvent::AIO; |
33 | |
33 | |
34 | # EV integration |
34 | # EV integration |
35 | my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
35 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
36 | |
36 | |
37 | # Event integration |
37 | # Event integration |
38 | Event->io (fd => IO::AIO::poll_fileno, |
38 | Event->io (fd => IO::AIO::poll_fileno, |
39 | poll => 'r', |
39 | poll => 'r', |
40 | cb => \&IO::AIO::poll_cb); |
40 | cb => \&IO::AIO::poll_cb); |
… | |
… | |
52 | \&IO::AIO::poll_cb); |
52 | \&IO::AIO::poll_cb); |
53 | |
53 | |
54 | =head1 DESCRIPTION |
54 | =head1 DESCRIPTION |
55 | |
55 | |
56 | This module implements asynchronous I/O using whatever means your |
56 | This module implements asynchronous I/O using whatever means your |
57 | operating system supports. |
57 | operating system supports. It is implemented as an interface to C<libeio> |
|
|
58 | (L<http://software.schmorp.de/pkg/libeio.html>). |
58 | |
59 | |
59 | Asynchronous means that operations that can normally block your program |
60 | Asynchronous means that operations that can normally block your program |
60 | (e.g. reading from disk) will be done asynchronously: the operation |
61 | (e.g. reading from disk) will be done asynchronously: the operation |
61 | will still block, but you can do something else in the meantime. This |
62 | will still block, but you can do something else in the meantime. This |
62 | is extremely useful for programs that need to stay interactive even |
63 | is extremely useful for programs that need to stay interactive even |
… | |
… | |
66 | on a RAID volume or over NFS when you do a number of stat operations |
67 | on a RAID volume or over NFS when you do a number of stat operations |
67 | concurrently. |
68 | concurrently. |
68 | |
69 | |
69 | While most of this works on all types of file descriptors (for |
70 | While most of this works on all types of file descriptors (for |
70 | example sockets), using these functions on file descriptors that |
71 | example sockets), using these functions on file descriptors that |
71 | support nonblocking operation (again, sockets, pipes etc.) is very |
72 | support nonblocking operation (again, sockets, pipes etc.) is |
72 | inefficient. Use an event loop for that (such as the L<Event|Event> |
73 | very inefficient. Use an event loop for that (such as the L<EV> |
73 | module): IO::AIO will naturally fit into such an event loop itself. |
74 | module): IO::AIO will naturally fit into such an event loop itself. |
74 | |
75 | |
75 | In this version, a number of threads are started that execute your |
76 | In this version, a number of threads are started that execute your |
76 | requests and signal their completion. You don't need thread support |
77 | requests and signal their completion. You don't need thread support |
77 | in perl, and the threads created by this module will not be visible |
78 | in perl, and the threads created by this module will not be visible |
… | |
… | |
87 | yourself, always call C<poll_cb> from within the same thread, or never |
88 | yourself, always call C<poll_cb> from within the same thread, or never |
88 | call C<poll_cb> (or other C<aio_> functions) recursively. |
89 | call C<poll_cb> (or other C<aio_> functions) recursively. |
89 | |
90 | |
90 | =head2 EXAMPLE |
91 | =head2 EXAMPLE |
91 | |
92 | |
92 | This is a simple example that uses the Event module and loads |
93 | This is a simple example that uses the EV module and loads |
93 | F</etc/passwd> asynchronously: |
94 | F</etc/passwd> asynchronously: |
94 | |
95 | |
95 | use Fcntl; |
96 | use Fcntl; |
96 | use Event; |
97 | use EV; |
97 | use IO::AIO; |
98 | use IO::AIO; |
98 | |
99 | |
99 | # register the IO::AIO callback with Event |
100 | # register the IO::AIO callback with EV |
100 | Event->io (fd => IO::AIO::poll_fileno, |
101 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
101 | poll => 'r', |
|
|
102 | cb => \&IO::AIO::poll_cb); |
|
|
103 | |
102 | |
104 | # queue the request to open /etc/passwd |
103 | # queue the request to open /etc/passwd |
105 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
104 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
106 | my $fh = shift |
105 | my $fh = shift |
107 | or die "error while opening: $!"; |
106 | or die "error while opening: $!"; |
… | |
… | |
119 | |
118 | |
120 | # file contents now in $contents |
119 | # file contents now in $contents |
121 | print $contents; |
120 | print $contents; |
122 | |
121 | |
123 | # exit event loop and program |
122 | # exit event loop and program |
124 | Event::unloop; |
123 | EV::unloop; |
125 | }; |
124 | }; |
126 | }; |
125 | }; |
127 | |
126 | |
128 | # possibly queue up other requests, or open GUI windows, |
127 | # possibly queue up other requests, or open GUI windows, |
129 | # check for sockets etc. etc. |
128 | # check for sockets etc. etc. |
130 | |
129 | |
131 | # process events as long as there are some: |
130 | # process events as long as there are some: |
132 | Event::loop; |
131 | EV::loop; |
133 | |
132 | |
134 | =head1 REQUEST ANATOMY AND LIFETIME |
133 | =head1 REQUEST ANATOMY AND LIFETIME |
135 | |
134 | |
136 | Every C<aio_*> function creates a request. which is a C data structure not |
135 | Every C<aio_*> function creates a request. which is a C data structure not |
137 | directly visible to Perl. |
136 | directly visible to Perl. |
… | |
… | |
193 | use strict 'vars'; |
192 | use strict 'vars'; |
194 | |
193 | |
195 | use base 'Exporter'; |
194 | use base 'Exporter'; |
196 | |
195 | |
197 | BEGIN { |
196 | BEGIN { |
198 | our $VERSION = '3.19'; |
197 | our $VERSION = '3.23'; |
199 | |
198 | |
200 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
199 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
201 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir |
200 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
202 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
201 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
203 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
202 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
204 | aio_rename aio_link aio_move aio_copy aio_group |
203 | aio_rename aio_link aio_move aio_copy aio_group |
205 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
204 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
206 | aio_chmod aio_utime aio_truncate); |
205 | aio_chmod aio_utime aio_truncate); |
… | |
… | |
533 | |
532 | |
534 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
533 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
535 | directory (i.e. opendir + readdir + closedir). The entries will not be |
534 | directory (i.e. opendir + readdir + closedir). The entries will not be |
536 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
535 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
537 | |
536 | |
538 | The callback a single argument which is either C<undef> or an array-ref |
537 | The callback is passed a single argument which is either C<undef> or an |
539 | with the filenames. |
538 | array-ref with the filenames. |
|
|
539 | |
|
|
540 | |
|
|
541 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
542 | |
|
|
543 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune |
|
|
544 | behaviour and output format. In case of an error, C<$entries> will be |
|
|
545 | C<undef>. |
|
|
546 | |
|
|
547 | The flags are a combination of the following constants, ORed together (the |
|
|
548 | flags will also be passed to the callback, possibly modified): |
|
|
549 | |
|
|
550 | =over 4 |
|
|
551 | |
|
|
552 | =item IO::AIO::READDIR_DENTS |
|
|
553 | |
|
|
554 | When this flag is off, then the callback gets an arrayref with of names |
|
|
555 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
|
|
556 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
|
|
557 | entry in more detail. |
|
|
558 | |
|
|
559 | C<$name> is the name of the entry. |
|
|
560 | |
|
|
561 | C<$type> is one of the C<IO::AIO::DT_xxx> constants: |
|
|
562 | |
|
|
563 | C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>, |
|
|
564 | C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>, |
|
|
565 | C<IO::AIO::DT_WHT>. |
|
|
566 | |
|
|
567 | C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
|
|
568 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
|
|
569 | scalars are read-only: you can not modify them. |
|
|
570 | |
|
|
571 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
572 | bit inode numbers and 32 bit perls). This field has unspecified content on |
|
|
573 | systems that do not deliver the inode information. |
|
|
574 | |
|
|
575 | =item IO::AIO::READDIR_DIRS_FIRST |
|
|
576 | |
|
|
577 | When this flag is set, then the names will be returned in an order where |
|
|
578 | likely directories come first. This is useful when you need to quickly |
|
|
579 | find directories, or you want to find all directories while avoiding to |
|
|
580 | stat() each entry. |
|
|
581 | |
|
|
582 | If the system returns type information in readdir, then this is used |
|
|
583 | to find directories directly. Otherwise, likely directories are files |
|
|
584 | beginning with ".", or otherwise files with no dots, of which files with |
|
|
585 | short names are tried first. |
|
|
586 | |
|
|
587 | =item IO::AIO::READDIR_STAT_ORDER |
|
|
588 | |
|
|
589 | When this flag is set, then the names will be returned in an order |
|
|
590 | suitable for stat()'ing each one. That is, when you plan to stat() |
|
|
591 | all files in the given directory, then the returned order will likely |
|
|
592 | be fastest. |
|
|
593 | |
|
|
594 | If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then |
|
|
595 | the likely dirs come first, resulting in a less optimal stat order. |
|
|
596 | |
|
|
597 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
598 | |
|
|
599 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
|
|
600 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
|
|
601 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
|
|
602 | C<$type>'s are known, which can be used to speed up some algorithms. |
|
|
603 | |
|
|
604 | =back |
540 | |
605 | |
541 | |
606 | |
542 | =item aio_load $path, $data, $callback->($status) |
607 | =item aio_load $path, $data, $callback->($status) |
543 | |
608 | |
544 | This is a composite request that tries to fully load the given file into |
609 | This is a composite request that tries to fully load the given file into |
… | |
… | |
591 | my $grp = aio_group $cb; |
656 | my $grp = aio_group $cb; |
592 | |
657 | |
593 | aioreq_pri $pri; |
658 | aioreq_pri $pri; |
594 | add $grp aio_open $src, O_RDONLY, 0, sub { |
659 | add $grp aio_open $src, O_RDONLY, 0, sub { |
595 | if (my $src_fh = $_[0]) { |
660 | if (my $src_fh = $_[0]) { |
596 | my @stat = stat $src_fh; |
661 | my @stat = stat $src_fh; # hmm, might bock over nfs? |
597 | |
662 | |
598 | aioreq_pri $pri; |
663 | aioreq_pri $pri; |
599 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
664 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
600 | if (my $dst_fh = $_[0]) { |
665 | if (my $dst_fh = $_[0]) { |
601 | aioreq_pri $pri; |
666 | aioreq_pri $pri; |
602 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
667 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
603 | if ($_[0] == $stat[7]) { |
668 | if ($_[0] == $stat[7]) { |
604 | $grp->result (0); |
669 | $grp->result (0); |
605 | close $src_fh; |
670 | close $src_fh; |
606 | |
671 | |
607 | # those should not normally block. should. should. |
672 | my $ch = sub { |
608 | utime $stat[8], $stat[9], $dst; |
673 | aioreq_pri $pri; |
609 | chmod $stat[2] & 07777, $dst_fh; |
674 | add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { |
610 | chown $stat[4], $stat[5], $dst_fh; |
675 | aioreq_pri $pri; |
|
|
676 | add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub { |
|
|
677 | aioreq_pri $pri; |
|
|
678 | add $grp aio_close $dst_fh; |
|
|
679 | } |
|
|
680 | }; |
|
|
681 | }; |
611 | |
682 | |
612 | aioreq_pri $pri; |
683 | aioreq_pri $pri; |
613 | add $grp aio_close $dst_fh; |
684 | add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub { |
|
|
685 | if ($_[0] < 0 && $! == ENOSYS) { |
|
|
686 | aioreq_pri $pri; |
|
|
687 | add $grp aio_utime $dst, $stat[8], $stat[9], $ch; |
|
|
688 | } else { |
|
|
689 | $ch->(); |
|
|
690 | } |
|
|
691 | }; |
614 | } else { |
692 | } else { |
615 | $grp->result (-1); |
693 | $grp->result (-1); |
616 | close $src_fh; |
694 | close $src_fh; |
617 | close $dst_fh; |
695 | close $dst_fh; |
618 | |
696 | |
… | |
… | |
696 | |
774 | |
697 | Implementation notes. |
775 | Implementation notes. |
698 | |
776 | |
699 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
777 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
700 | |
778 | |
|
|
779 | If readdir returns file type information, then this is used directly to |
|
|
780 | find directories. |
|
|
781 | |
701 | After reading the directory, the modification time, size etc. of the |
782 | Otherwise, after reading the directory, the modification time, size etc. |
702 | directory before and after the readdir is checked, and if they match (and |
783 | of the directory before and after the readdir is checked, and if they |
703 | isn't the current time), the link count will be used to decide how many |
784 | match (and isn't the current time), the link count will be used to decide |
704 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
785 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
705 | of subdirectories will be assumed. |
786 | number of subdirectories will be assumed. |
706 | |
787 | |
707 | Then entries will be sorted into likely directories (everything without |
788 | Then entries will be sorted into likely directories a non-initial dot |
708 | a non-initial dot currently) and likely non-directories (everything |
789 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
709 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
790 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
710 | likely directories first. If that succeeds, it assumes that the entry |
791 | in order of their inode numbers. If that succeeds, it assumes that the |
711 | is a directory or a symlink to directory (which will be checked |
792 | entry is a directory or a symlink to directory (which will be checked |
712 | seperately). This is often faster than stat'ing the entry itself because |
793 | seperately). This is often faster than stat'ing the entry itself because |
713 | filesystems might detect the type of the entry without reading the inode |
794 | filesystems might detect the type of the entry without reading the inode |
714 | data (e.g. ext2fs filetype feature). |
795 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
|
|
796 | the filetype information on readdir. |
715 | |
797 | |
716 | If the known number of directories (link count - 2) has been reached, the |
798 | If the known number of directories (link count - 2) has been reached, the |
717 | rest of the entries is assumed to be non-directories. |
799 | rest of the entries is assumed to be non-directories. |
718 | |
800 | |
719 | This only works with certainty on POSIX (= UNIX) filesystems, which |
801 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
741 | my $now = time; |
823 | my $now = time; |
742 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
824 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
743 | |
825 | |
744 | # read the directory entries |
826 | # read the directory entries |
745 | aioreq_pri $pri; |
827 | aioreq_pri $pri; |
746 | add $grp aio_readdir $path, sub { |
828 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
747 | my $entries = shift |
829 | my $entries = shift |
748 | or return $grp->result (); |
830 | or return $grp->result (); |
749 | |
831 | |
750 | # stat the dir another time |
832 | # stat the dir another time |
751 | aioreq_pri $pri; |
833 | aioreq_pri $pri; |
… | |
… | |
757 | # take the slow route if anything looks fishy |
839 | # take the slow route if anything looks fishy |
758 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
840 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
759 | $ndirs = -1; |
841 | $ndirs = -1; |
760 | } else { |
842 | } else { |
761 | # if nlink == 2, we are finished |
843 | # if nlink == 2, we are finished |
762 | # on non-posix-fs's, we rely on nlink < 2 |
844 | # for non-posix-fs's, we rely on nlink < 2 |
763 | $ndirs = (stat _)[3] - 2 |
845 | $ndirs = (stat _)[3] - 2 |
764 | or return $grp->result ([], $entries); |
846 | or return $grp->result ([], $entries); |
765 | } |
847 | } |
766 | |
848 | |
767 | # sort into likely dirs and likely nondirs |
|
|
768 | # dirs == files without ".", short entries first |
|
|
769 | $entries = [map $_->[0], |
|
|
770 | sort { $b->[1] cmp $a->[1] } |
|
|
771 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
772 | @$entries]; |
|
|
773 | |
|
|
774 | my (@dirs, @nondirs); |
849 | my (@dirs, @nondirs); |
775 | |
850 | |
776 | my $statgrp = add $grp aio_group sub { |
851 | my $statgrp = add $grp aio_group sub { |
777 | $grp->result (\@dirs, \@nondirs); |
852 | $grp->result (\@dirs, \@nondirs); |
778 | }; |
853 | }; |
779 | |
854 | |
780 | limit $statgrp $maxreq; |
855 | limit $statgrp $maxreq; |
781 | feed $statgrp sub { |
856 | feed $statgrp sub { |
782 | return unless @$entries; |
857 | return unless @$entries; |
783 | my $entry = pop @$entries; |
858 | my $entry = shift @$entries; |
784 | |
859 | |
785 | aioreq_pri $pri; |
860 | aioreq_pri $pri; |
786 | add $statgrp aio_stat "$path/$entry/.", sub { |
861 | add $statgrp aio_stat "$path/$entry/.", sub { |
787 | if ($_[0] < 0) { |
862 | if ($_[0] < 0) { |
788 | push @nondirs, $entry; |
863 | push @nondirs, $entry; |
… | |
… | |
969 | =item cancel $req |
1044 | =item cancel $req |
970 | |
1045 | |
971 | Cancels the request, if possible. Has the effect of skipping execution |
1046 | Cancels the request, if possible. Has the effect of skipping execution |
972 | when entering the B<execute> state and skipping calling the callback when |
1047 | when entering the B<execute> state and skipping calling the callback when |
973 | entering the the B<result> state, but will leave the request otherwise |
1048 | entering the the B<result> state, but will leave the request otherwise |
974 | untouched. That means that requests that currently execute will not be |
1049 | untouched (with the exception of readdir). That means that requests that |
975 | stopped and resources held by the request will not be freed prematurely. |
1050 | currently execute will not be stopped and resources held by the request |
|
|
1051 | will not be freed prematurely. |
976 | |
1052 | |
977 | =item cb $req $callback->(...) |
1053 | =item cb $req $callback->(...) |
978 | |
1054 | |
979 | Replace (or simply set) the callback registered to the request. |
1055 | Replace (or simply set) the callback registered to the request. |
980 | |
1056 | |
… | |
… | |
1131 | =over 4 |
1207 | =over 4 |
1132 | |
1208 | |
1133 | =item $fileno = IO::AIO::poll_fileno |
1209 | =item $fileno = IO::AIO::poll_fileno |
1134 | |
1210 | |
1135 | Return the I<request result pipe file descriptor>. This filehandle must be |
1211 | Return the I<request result pipe file descriptor>. This filehandle must be |
1136 | polled for reading by some mechanism outside this module (e.g. Event or |
1212 | polled for reading by some mechanism outside this module (e.g. EV, Glib, |
1137 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
1213 | select and so on, see below or the SYNOPSIS). If the pipe becomes readable |
1138 | to call C<poll_cb> to check the results. |
1214 | you have to call C<poll_cb> to check the results. |
1139 | |
1215 | |
1140 | See C<poll_cb> for an example. |
1216 | See C<poll_cb> for an example. |
1141 | |
1217 | |
1142 | =item IO::AIO::poll_cb |
1218 | =item IO::AIO::poll_cb |
1143 | |
1219 | |
… | |
… | |
1150 | If not all requests were processed for whatever reason, the filehandle |
1226 | If not all requests were processed for whatever reason, the filehandle |
1151 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1227 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1152 | do anything special to have it called later. |
1228 | do anything special to have it called later. |
1153 | |
1229 | |
1154 | Example: Install an Event watcher that automatically calls |
1230 | Example: Install an Event watcher that automatically calls |
1155 | IO::AIO::poll_cb with high priority: |
1231 | IO::AIO::poll_cb with high priority (more examples can be found in the |
|
|
1232 | SYNOPSIS section, at the top of this document): |
1156 | |
1233 | |
1157 | Event->io (fd => IO::AIO::poll_fileno, |
1234 | Event->io (fd => IO::AIO::poll_fileno, |
1158 | poll => 'r', async => 1, |
1235 | poll => 'r', async => 1, |
1159 | cb => \&IO::AIO::poll_cb); |
1236 | cb => \&IO::AIO::poll_cb); |
1160 | |
1237 | |