… | |
… | |
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. |
… | |
… | |
187 | |
186 | |
188 | package IO::AIO; |
187 | package IO::AIO; |
189 | |
188 | |
190 | use Carp (); |
189 | use Carp (); |
191 | |
190 | |
192 | no warnings; |
191 | use common::sense; |
193 | use strict 'vars'; |
|
|
194 | |
192 | |
195 | use base 'Exporter'; |
193 | use base 'Exporter'; |
196 | |
194 | |
197 | BEGIN { |
195 | BEGIN { |
198 | our $VERSION = '3.02'; |
196 | our $VERSION = '3.3'; |
199 | |
197 | |
200 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
198 | 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 |
199 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
202 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
200 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
203 | aio_fdatasync aio_pathsync aio_readahead |
201 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
204 | aio_rename aio_link aio_move aio_copy aio_group |
202 | aio_rename aio_link aio_move aio_copy aio_group |
205 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
203 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
206 | aio_chmod aio_utime aio_truncate); |
204 | aio_chmod aio_utime aio_truncate); |
207 | |
205 | |
208 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
206 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
209 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
207 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
210 | min_parallel max_parallel max_idle |
208 | min_parallel max_parallel max_idle |
211 | nreqs nready npending nthreads |
209 | nreqs nready npending nthreads |
212 | max_poll_time max_poll_reqs); |
210 | max_poll_time max_poll_reqs |
|
|
211 | sendfile fadvise); |
|
|
212 | |
|
|
213 | push @AIO_REQ, qw(aio_busy); # not exported |
213 | |
214 | |
214 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
215 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
215 | |
216 | |
216 | require XSLoader; |
217 | require XSLoader; |
217 | XSLoader::load ("IO::AIO", $VERSION); |
218 | XSLoader::load ("IO::AIO", $VERSION); |
… | |
… | |
224 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
225 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
225 | with the same name (sans C<aio_>). The arguments are similar or identical, |
226 | with the same name (sans C<aio_>). The arguments are similar or identical, |
226 | and they all accept an additional (and optional) C<$callback> argument |
227 | and they all accept an additional (and optional) C<$callback> argument |
227 | which must be a code reference. This code reference will get called with |
228 | which must be a code reference. This code reference will get called with |
228 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
229 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
229 | perl, which usually delivers "false") as it's sole argument when the given |
230 | perl, which usually delivers "false") as its sole argument after the given |
230 | syscall has been executed asynchronously. |
231 | syscall has been executed asynchronously. |
231 | |
232 | |
232 | All functions expecting a filehandle keep a copy of the filehandle |
233 | All functions expecting a filehandle keep a copy of the filehandle |
233 | internally until the request has finished. |
234 | internally until the request has finished. |
234 | |
235 | |
… | |
… | |
248 | your pathnames to the locale (or other) encoding in effect in the user |
249 | your pathnames to the locale (or other) encoding in effect in the user |
249 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
250 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
250 | use something else to ensure your scalar has the correct contents. |
251 | use something else to ensure your scalar has the correct contents. |
251 | |
252 | |
252 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
253 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
253 | handles correctly wether it is set or not. |
254 | handles correctly whether it is set or not. |
254 | |
255 | |
255 | =over 4 |
256 | =over 4 |
256 | |
257 | |
257 | =item $prev_pri = aioreq_pri [$pri] |
258 | =item $prev_pri = aioreq_pri [$pri] |
258 | |
259 | |
… | |
… | |
336 | |
337 | |
337 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
338 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
338 | |
339 | |
339 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
340 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
340 | |
341 | |
341 | Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset> |
342 | Reads or writes C<$length> bytes from or to the specified C<$fh> and |
342 | into the scalar given by C<$data> and offset C<$dataoffset> and calls the |
343 | C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> |
343 | callback without the actual number of bytes read (or -1 on error, just |
344 | and calls the callback without the actual number of bytes read (or -1 on |
344 | like the syscall). |
345 | error, just like the syscall). |
|
|
346 | |
|
|
347 | C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to |
|
|
348 | offset plus the actual number of bytes read. |
345 | |
349 | |
346 | If C<$offset> is undefined, then the current file descriptor offset will |
350 | If C<$offset> is undefined, then the current file descriptor offset will |
347 | be used (and updated), otherwise the file descriptor offset will not be |
351 | be used (and updated), otherwise the file descriptor offset will not be |
348 | changed by these calls. |
352 | changed by these calls. |
349 | |
353 | |
350 | If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>. |
354 | If C<$length> is undefined in C<aio_write>, use the remaining length of |
|
|
355 | C<$data>. |
351 | |
356 | |
352 | If C<$dataoffset> is less than zero, it will be counted from the end of |
357 | If C<$dataoffset> is less than zero, it will be counted from the end of |
353 | C<$data>. |
358 | C<$data>. |
354 | |
359 | |
355 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
360 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
… | |
… | |
527 | |
532 | |
528 | 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 |
529 | directory (i.e. opendir + readdir + closedir). The entries will not be |
534 | directory (i.e. opendir + readdir + closedir). The entries will not be |
530 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
535 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
531 | |
536 | |
532 | 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 |
533 | 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 |
534 | |
605 | |
535 | |
606 | |
536 | =item aio_load $path, $data, $callback->($status) |
607 | =item aio_load $path, $data, $callback->($status) |
537 | |
608 | |
538 | 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 |
… | |
… | |
563 | |
634 | |
564 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
635 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
565 | |
636 | |
566 | Try to copy the I<file> (directories not supported as either source or |
637 | Try to copy the I<file> (directories not supported as either source or |
567 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
638 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
568 | the C<0> (error) or C<-1> ok. |
639 | a status of C<0> (ok) or C<-1> (error, see C<$!>). |
569 | |
640 | |
570 | This is a composite request that it creates the destination file with |
641 | This is a composite request that creates the destination file with |
571 | mode 0200 and copies the contents of the source file into it using |
642 | mode 0200 and copies the contents of the source file into it using |
572 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
643 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
573 | uid/gid, in that order. |
644 | uid/gid, in that order. |
574 | |
645 | |
575 | If an error occurs, the partial destination file will be unlinked, if |
646 | If an error occurs, the partial destination file will be unlinked, if |
… | |
… | |
585 | my $grp = aio_group $cb; |
656 | my $grp = aio_group $cb; |
586 | |
657 | |
587 | aioreq_pri $pri; |
658 | aioreq_pri $pri; |
588 | add $grp aio_open $src, O_RDONLY, 0, sub { |
659 | add $grp aio_open $src, O_RDONLY, 0, sub { |
589 | if (my $src_fh = $_[0]) { |
660 | if (my $src_fh = $_[0]) { |
590 | my @stat = stat $src_fh; |
661 | my @stat = stat $src_fh; # hmm, might block over nfs? |
591 | |
662 | |
592 | aioreq_pri $pri; |
663 | aioreq_pri $pri; |
593 | 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 { |
594 | if (my $dst_fh = $_[0]) { |
665 | if (my $dst_fh = $_[0]) { |
595 | aioreq_pri $pri; |
666 | aioreq_pri $pri; |
596 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
667 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
597 | if ($_[0] == $stat[7]) { |
668 | if ($_[0] == $stat[7]) { |
598 | $grp->result (0); |
669 | $grp->result (0); |
599 | close $src_fh; |
670 | close $src_fh; |
600 | |
671 | |
601 | # those should not normally block. should. should. |
672 | my $ch = sub { |
602 | utime $stat[8], $stat[9], $dst; |
673 | aioreq_pri $pri; |
603 | chmod $stat[2] & 07777, $dst_fh; |
674 | add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { |
604 | 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 | }; |
605 | |
682 | |
606 | aioreq_pri $pri; |
683 | aioreq_pri $pri; |
607 | 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 | }; |
608 | } else { |
692 | } else { |
609 | $grp->result (-1); |
693 | $grp->result (-1); |
610 | close $src_fh; |
694 | close $src_fh; |
611 | close $dst_fh; |
695 | close $dst_fh; |
612 | |
696 | |
… | |
… | |
629 | |
713 | |
630 | =item aio_move $srcpath, $dstpath, $callback->($status) |
714 | =item aio_move $srcpath, $dstpath, $callback->($status) |
631 | |
715 | |
632 | Try to move the I<file> (directories not supported as either source or |
716 | Try to move the I<file> (directories not supported as either source or |
633 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
717 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
634 | the C<0> (error) or C<-1> ok. |
718 | a status of C<0> (ok) or C<-1> (error, see C<$!>). |
635 | |
719 | |
636 | This is a composite request that tries to rename(2) the file first. If |
720 | This is a composite request that tries to rename(2) the file first; if |
637 | rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if |
721 | rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if |
638 | that is successful, unlinking the C<$srcpath>. |
722 | that is successful, unlinks the C<$srcpath>. |
639 | |
723 | |
640 | =cut |
724 | =cut |
641 | |
725 | |
642 | sub aio_move($$;$) { |
726 | sub aio_move($$;$) { |
643 | my ($src, $dst, $cb) = @_; |
727 | my ($src, $dst, $cb) = @_; |
… | |
… | |
690 | |
774 | |
691 | Implementation notes. |
775 | Implementation notes. |
692 | |
776 | |
693 | 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. |
694 | |
778 | |
|
|
779 | If readdir returns file type information, then this is used directly to |
|
|
780 | find directories. |
|
|
781 | |
695 | After reading the directory, the modification time, size etc. of the |
782 | Otherwise, after reading the directory, the modification time, size etc. |
696 | 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 |
697 | 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 |
698 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
785 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
699 | of subdirectories will be assumed. |
786 | number of subdirectories will be assumed. |
700 | |
787 | |
701 | Then entries will be sorted into likely directories (everything without |
788 | Then entries will be sorted into likely directories a non-initial dot |
702 | a non-initial dot currently) and likely non-directories (everything |
789 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
703 | 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, |
704 | 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 |
705 | 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 |
706 | 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 |
707 | 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 |
708 | 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. |
709 | |
797 | |
710 | 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 |
711 | rest of the entries is assumed to be non-directories. |
799 | rest of the entries is assumed to be non-directories. |
712 | |
800 | |
713 | This only works with certainty on POSIX (= UNIX) filesystems, which |
801 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
735 | my $now = time; |
823 | my $now = time; |
736 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
824 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
737 | |
825 | |
738 | # read the directory entries |
826 | # read the directory entries |
739 | aioreq_pri $pri; |
827 | aioreq_pri $pri; |
740 | add $grp aio_readdir $path, sub { |
828 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
741 | my $entries = shift |
829 | my $entries = shift |
742 | or return $grp->result (); |
830 | or return $grp->result (); |
743 | |
831 | |
744 | # stat the dir another time |
832 | # stat the dir another time |
745 | aioreq_pri $pri; |
833 | aioreq_pri $pri; |
… | |
… | |
751 | # take the slow route if anything looks fishy |
839 | # take the slow route if anything looks fishy |
752 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
840 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
753 | $ndirs = -1; |
841 | $ndirs = -1; |
754 | } else { |
842 | } else { |
755 | # if nlink == 2, we are finished |
843 | # if nlink == 2, we are finished |
756 | # on non-posix-fs's, we rely on nlink < 2 |
844 | # for non-posix-fs's, we rely on nlink < 2 |
757 | $ndirs = (stat _)[3] - 2 |
845 | $ndirs = (stat _)[3] - 2 |
758 | or return $grp->result ([], $entries); |
846 | or return $grp->result ([], $entries); |
759 | } |
847 | } |
760 | |
848 | |
761 | # sort into likely dirs and likely nondirs |
|
|
762 | # dirs == files without ".", short entries first |
|
|
763 | $entries = [map $_->[0], |
|
|
764 | sort { $b->[1] cmp $a->[1] } |
|
|
765 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
766 | @$entries]; |
|
|
767 | |
|
|
768 | my (@dirs, @nondirs); |
849 | my (@dirs, @nondirs); |
769 | |
850 | |
770 | my $statgrp = add $grp aio_group sub { |
851 | my $statgrp = add $grp aio_group sub { |
771 | $grp->result (\@dirs, \@nondirs); |
852 | $grp->result (\@dirs, \@nondirs); |
772 | }; |
853 | }; |
773 | |
854 | |
774 | limit $statgrp $maxreq; |
855 | limit $statgrp $maxreq; |
775 | feed $statgrp sub { |
856 | feed $statgrp sub { |
776 | return unless @$entries; |
857 | return unless @$entries; |
777 | my $entry = pop @$entries; |
858 | my $entry = shift @$entries; |
778 | |
859 | |
779 | aioreq_pri $pri; |
860 | aioreq_pri $pri; |
780 | add $statgrp aio_stat "$path/$entry/.", sub { |
861 | add $statgrp aio_stat "$path/$entry/.", sub { |
781 | if ($_[0] < 0) { |
862 | if ($_[0] < 0) { |
782 | push @nondirs, $entry; |
863 | push @nondirs, $entry; |
… | |
… | |
855 | callback with the fdatasync result code. |
936 | callback with the fdatasync result code. |
856 | |
937 | |
857 | If this call isn't available because your OS lacks it or it couldn't be |
938 | If this call isn't available because your OS lacks it or it couldn't be |
858 | detected, it will be emulated by calling C<fsync> instead. |
939 | detected, it will be emulated by calling C<fsync> instead. |
859 | |
940 | |
|
|
941 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
942 | |
|
|
943 | Sync the data portion of the file specified by C<$offset> and C<$length> |
|
|
944 | to disk (but NOT the metadata), by calling the Linux-specific |
|
|
945 | sync_file_range call. If sync_file_range is not available or it returns |
|
|
946 | ENOSYS, then fdatasync or fsync is being substituted. |
|
|
947 | |
|
|
948 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
|
|
949 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
|
|
950 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
|
|
951 | manpage for details. |
|
|
952 | |
860 | =item aio_pathsync $path, $callback->($status) |
953 | =item aio_pathsync $path, $callback->($status) |
861 | |
954 | |
862 | This request tries to open, fsync and close the given path. This is a |
955 | This request tries to open, fsync and close the given path. This is a |
863 | composite request intended tosync directories after directory operations |
956 | composite request intended to sync directories after directory operations |
864 | (E.g. rename). This might not work on all operating systems or have any |
957 | (E.g. rename). This might not work on all operating systems or have any |
865 | specific effect, but usually it makes sure that directory changes get |
958 | specific effect, but usually it makes sure that directory changes get |
866 | written to disc. It works for anything that can be opened for read-only, |
959 | written to disc. It works for anything that can be opened for read-only, |
867 | not just directories. |
960 | not just directories. |
|
|
961 | |
|
|
962 | Future versions of this function might fall back to other methods when |
|
|
963 | C<fsync> on the directory fails (such as calling C<sync>). |
868 | |
964 | |
869 | Passes C<0> when everything went ok, and C<-1> on error. |
965 | Passes C<0> when everything went ok, and C<-1> on error. |
870 | |
966 | |
871 | =cut |
967 | =cut |
872 | |
968 | |
… | |
… | |
951 | =item cancel $req |
1047 | =item cancel $req |
952 | |
1048 | |
953 | Cancels the request, if possible. Has the effect of skipping execution |
1049 | Cancels the request, if possible. Has the effect of skipping execution |
954 | when entering the B<execute> state and skipping calling the callback when |
1050 | when entering the B<execute> state and skipping calling the callback when |
955 | entering the the B<result> state, but will leave the request otherwise |
1051 | entering the the B<result> state, but will leave the request otherwise |
956 | untouched. That means that requests that currently execute will not be |
1052 | untouched (with the exception of readdir). That means that requests that |
957 | stopped and resources held by the request will not be freed prematurely. |
1053 | currently execute will not be stopped and resources held by the request |
|
|
1054 | will not be freed prematurely. |
958 | |
1055 | |
959 | =item cb $req $callback->(...) |
1056 | =item cb $req $callback->(...) |
960 | |
1057 | |
961 | Replace (or simply set) the callback registered to the request. |
1058 | Replace (or simply set) the callback registered to the request. |
962 | |
1059 | |
… | |
… | |
1013 | Their lifetime, simplified, looks like this: when they are empty, they |
1110 | Their lifetime, simplified, looks like this: when they are empty, they |
1014 | will finish very quickly. If they contain only requests that are in the |
1111 | will finish very quickly. If they contain only requests that are in the |
1015 | C<done> state, they will also finish. Otherwise they will continue to |
1112 | C<done> state, they will also finish. Otherwise they will continue to |
1016 | exist. |
1113 | exist. |
1017 | |
1114 | |
1018 | That means after creating a group you have some time to add requests. And |
1115 | That means after creating a group you have some time to add requests |
1019 | in the callbacks of those requests, you can add further requests to the |
1116 | (precisely before the callback has been invoked, which is only done within |
1020 | group. And only when all those requests have finished will the the group |
1117 | the C<poll_cb>). And in the callbacks of those requests, you can add |
1021 | itself finish. |
1118 | further requests to the group. And only when all those requests have |
|
|
1119 | finished will the the group itself finish. |
1022 | |
1120 | |
1023 | =over 4 |
1121 | =over 4 |
1024 | |
1122 | |
1025 | =item add $grp ... |
1123 | =item add $grp ... |
1026 | |
1124 | |
… | |
… | |
1059 | =item feed $grp $callback->($grp) |
1157 | =item feed $grp $callback->($grp) |
1060 | |
1158 | |
1061 | Sets a feeder/generator on this group: every group can have an attached |
1159 | Sets a feeder/generator on this group: every group can have an attached |
1062 | generator that generates requests if idle. The idea behind this is that, |
1160 | generator that generates requests if idle. The idea behind this is that, |
1063 | although you could just queue as many requests as you want in a group, |
1161 | although you could just queue as many requests as you want in a group, |
1064 | this might starve other requests for a potentially long time. For |
1162 | this might starve other requests for a potentially long time. For example, |
1065 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
1163 | C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, |
1066 | requests, delaying any later requests for a long time. |
1164 | delaying any later requests for a long time. |
1067 | |
1165 | |
1068 | To avoid this, and allow incremental generation of requests, you can |
1166 | To avoid this, and allow incremental generation of requests, you can |
1069 | instead a group and set a feeder on it that generates those requests. The |
1167 | instead a group and set a feeder on it that generates those requests. The |
1070 | feed callback will be called whenever there are few enough (see C<limit>, |
1168 | feed callback will be called whenever there are few enough (see C<limit>, |
1071 | below) requests active in the group itself and is expected to queue more |
1169 | below) requests active in the group itself and is expected to queue more |
… | |
… | |
1075 | not impose any limits). |
1173 | not impose any limits). |
1076 | |
1174 | |
1077 | If the feed does not queue more requests when called, it will be |
1175 | If the feed does not queue more requests when called, it will be |
1078 | automatically removed from the group. |
1176 | automatically removed from the group. |
1079 | |
1177 | |
1080 | If the feed limit is C<0>, it will be set to C<2> automatically. |
1178 | If the feed limit is C<0> when this method is called, it will be set to |
|
|
1179 | C<2> automatically. |
1081 | |
1180 | |
1082 | Example: |
1181 | Example: |
1083 | |
1182 | |
1084 | # stat all files in @files, but only ever use four aio requests concurrently: |
1183 | # stat all files in @files, but only ever use four aio requests concurrently: |
1085 | |
1184 | |
… | |
… | |
1097 | Sets the feeder limit for the group: The feeder will be called whenever |
1196 | Sets the feeder limit for the group: The feeder will be called whenever |
1098 | the group contains less than this many requests. |
1197 | the group contains less than this many requests. |
1099 | |
1198 | |
1100 | Setting the limit to C<0> will pause the feeding process. |
1199 | Setting the limit to C<0> will pause the feeding process. |
1101 | |
1200 | |
|
|
1201 | The default value for the limit is C<0>, but note that setting a feeder |
|
|
1202 | automatically bumps it up to C<2>. |
|
|
1203 | |
1102 | =back |
1204 | =back |
1103 | |
1205 | |
1104 | =head2 SUPPORT FUNCTIONS |
1206 | =head2 SUPPORT FUNCTIONS |
1105 | |
1207 | |
1106 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
1208 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
… | |
… | |
1108 | =over 4 |
1210 | =over 4 |
1109 | |
1211 | |
1110 | =item $fileno = IO::AIO::poll_fileno |
1212 | =item $fileno = IO::AIO::poll_fileno |
1111 | |
1213 | |
1112 | Return the I<request result pipe file descriptor>. This filehandle must be |
1214 | Return the I<request result pipe file descriptor>. This filehandle must be |
1113 | polled for reading by some mechanism outside this module (e.g. Event or |
1215 | polled for reading by some mechanism outside this module (e.g. EV, Glib, |
1114 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
1216 | select and so on, see below or the SYNOPSIS). If the pipe becomes readable |
1115 | to call C<poll_cb> to check the results. |
1217 | you have to call C<poll_cb> to check the results. |
1116 | |
1218 | |
1117 | See C<poll_cb> for an example. |
1219 | See C<poll_cb> for an example. |
1118 | |
1220 | |
1119 | =item IO::AIO::poll_cb |
1221 | =item IO::AIO::poll_cb |
1120 | |
1222 | |
1121 | Process some outstanding events on the result pipe. You have to call this |
1223 | Process some outstanding events on the result pipe. You have to call this |
1122 | regularly. Returns the number of events processed. Returns immediately |
1224 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
|
|
1225 | returned earlier for whatever reason. Returns immediately when no events |
1123 | when no events are outstanding. The amount of events processed depends on |
1226 | are outstanding. The amount of events processed depends on the settings of |
1124 | the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
1227 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
1125 | |
1228 | |
1126 | If not all requests were processed for whatever reason, the filehandle |
1229 | If not all requests were processed for whatever reason, the filehandle |
1127 | will still be ready when C<poll_cb> returns. |
1230 | will still be ready when C<poll_cb> returns, so normally you don't have to |
|
|
1231 | do anything special to have it called later. |
1128 | |
1232 | |
1129 | Example: Install an Event watcher that automatically calls |
1233 | Example: Install an Event watcher that automatically calls |
1130 | IO::AIO::poll_cb with high priority: |
1234 | IO::AIO::poll_cb with high priority (more examples can be found in the |
|
|
1235 | SYNOPSIS section, at the top of this document): |
1131 | |
1236 | |
1132 | Event->io (fd => IO::AIO::poll_fileno, |
1237 | Event->io (fd => IO::AIO::poll_fileno, |
1133 | poll => 'r', async => 1, |
1238 | poll => 'r', async => 1, |
1134 | cb => \&IO::AIO::poll_cb); |
1239 | cb => \&IO::AIO::poll_cb); |
1135 | |
1240 | |
… | |
… | |
1289 | |
1394 | |
1290 | =item IO::AIO::npending |
1395 | =item IO::AIO::npending |
1291 | |
1396 | |
1292 | Returns the number of requests currently in the pending state (executed, |
1397 | Returns the number of requests currently in the pending state (executed, |
1293 | but not yet processed by poll_cb). |
1398 | but not yet processed by poll_cb). |
|
|
1399 | |
|
|
1400 | =back |
|
|
1401 | |
|
|
1402 | =head3 MISCELLANEOUS FUNCTIONS |
|
|
1403 | |
|
|
1404 | IO::AIO implements some functions that might be useful, but are not |
|
|
1405 | asynchronous. |
|
|
1406 | |
|
|
1407 | =over 4 |
|
|
1408 | |
|
|
1409 | =item IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
1410 | |
|
|
1411 | Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>, |
|
|
1412 | but is blocking (this makes most sense if you know the input data is |
|
|
1413 | likely cached already and the output filehandle is set to non-blocking |
|
|
1414 | operations). |
|
|
1415 | |
|
|
1416 | Returns the number of bytes copied, or C<-1> on error. |
|
|
1417 | |
|
|
1418 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
1419 | |
|
|
1420 | Simply calls the C<posix_fadvise> function (see it's |
|
|
1421 | manpage for details). The following advice constants are |
|
|
1422 | avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
|
|
1423 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
|
|
1424 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
|
|
1425 | |
|
|
1426 | On systems that do not implement C<posix_fadvise>, this function returns |
|
|
1427 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
1294 | |
1428 | |
1295 | =back |
1429 | =back |
1296 | |
1430 | |
1297 | =cut |
1431 | =cut |
1298 | |
1432 | |