--- IO-AIO/AIO.pm 2006/10/25 17:57:30 1.77 +++ IO-AIO/AIO.pm 2006/10/28 01:40:30 1.85 @@ -53,12 +53,28 @@ This module implements asynchronous I/O using whatever means your operating system supports. +Asynchronous means that operations that can normally block your program +(e.g. reading from disk) will be done asynchronously: the operation +will still block, but you can do something else in the meantime. This +is extremely useful for programs that need to stay interactive even +when doing heavy I/O (GUI programs, high performance network servers +etc.), but can also be used to easily do operations in parallel that are +normally done sequentially, e.g. stat'ing many files, which is much faster +on a RAID volume or over NFS when you do a number of stat operations +concurrently. + +While this works on all types of file descriptors (for example sockets), +using these functions on file descriptors that support nonblocking +operation (again, sockets, pipes etc.) is very inefficient. Use an event +loop for that (such as the L module): IO::AIO will naturally +fit into such an event loop itself. + In this version, a number of threads are started that execute your requests and signal their completion. You don't need thread support in perl, and the threads created by this module will not be visible to perl. In the future, this module might make use of the native aio functions available on many operating systems. However, they are often -not well-supported or restricted (Linux doesn't allow them on normal +not well-supported or restricted (GNU/Linux doesn't allow them on normal files currently, for example), and they would only support aio_read and aio_write, so the remaining functionality would have to be implemented using threads anyway. @@ -133,10 +149,10 @@ our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move - aio_group aio_nop); + aio_copy aio_group aio_nop aio_mknod); our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush - min_parallel max_parallel nreqs); + min_parallel max_parallel nreqs nready npending); @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; @@ -177,13 +193,16 @@ =over 4 -=item aioreq_pri $pri +=item $prev_pri = aioreq_pri [$pri] + +Returns the priority value that would be used for the next request and, if +C<$pri> is given, sets the priority for the next aio request. -Sets the priority for the next aio request. The default priority -is C<0>, the minimum and maximum priorities are C<-4> and C<4>, -respectively. Requests with higher priority will be serviced first. +The default priority is C<0>, the minimum and maximum priorities are C<-4> +and C<4>, respectively. Requests with higher priority will be serviced +first. -The priority will be reset to C<0> after each call to one of the C +The priority will be reset to C<0> after each call to one of the C functions. Example: open a file with low priority, then read something from it with @@ -264,74 +283,6 @@ print "read $_[0] bytes: <$buffer>\n"; }; -=item aio_move $srcpath, $dstpath, $callback->($status) - -Try to move the I (directories not supported as either source or -destination) from C<$srcpath> to C<$dstpath> and call the callback with -the C<0> (error) or C<-1> ok. - -This is a composite request that tries to rename(2) the file first. If -rename files with C, it creates the destination file with mode 0200 -and copies the contents of the source file into it using C, -followed by restoring atime, mtime, access mode and uid/gid, in that -order, and unlinking the C<$srcpath>. - -If an error occurs, the partial destination file will be unlinked, if -possible, except when setting atime, mtime, access mode and uid/gid, where -errors are being ignored. - -=cut - -sub aio_move($$$) { - my ($src, $dst, $cb) = @_; - - my $grp = aio_group $cb; - - add $grp aio_rename $src, $dst, sub { - if ($_[0] && $! == EXDEV) { - add $grp aio_open $src, O_RDONLY, 0, sub { - if (my $src_fh = $_[0]) { - my @stat = stat $src_fh; - - add $grp aio_open $dst, O_WRONLY, 0200, sub { - if (my $dst_fh = $_[0]) { - add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { - close $src_fh; - - if ($_[0] == $stat[7]) { - utime $stat[8], $stat[9], $dst; - chmod $stat[2] & 07777, $dst_fh; - chown $stat[4], $stat[5], $dst_fh; - close $dst_fh; - - add $grp aio_unlink $src, sub { - $grp->result ($_[0]); - }; - } else { - my $errno = $!; - add $grp aio_unlink $dst, sub { - $! = $errno; - $grp->result (-1); - }; - } - }; - } else { - $grp->result (-1); - } - }, - - } else { - $grp->result (-1); - } - }; - } else { - $grp->result ($_[0]); - } - }; - - $grp -} - =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts @@ -396,6 +347,14 @@ Asynchronously unlink (delete) a file and call the callback with the result code. +=item aio_mknod $path, $mode, $dev, $callback->($status) + +Asynchronously create a device node (or fifo). See mknod(2). + +The only portable (POSIX) way of calling this function is: + + aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... + =item aio_link $srcpath, $dstpath, $callback->($status) Asynchronously create a new link to the existing object at C<$srcpath> at @@ -425,6 +384,108 @@ The callback a single argument which is either C or an array-ref with the filenames. +=item aio_copy $srcpath, $dstpath, $callback->($status) + +Try to copy the I (directories not supported as either source or +destination) from C<$srcpath> to C<$dstpath> and call the callback with +the C<0> (error) or C<-1> ok. + +This is a composite request that it creates the destination file with +mode 0200 and copies the contents of the source file into it using +C, followed by restoring atime, mtime, access mode and +uid/gid, in that order. + +If an error occurs, the partial destination file will be unlinked, if +possible, except when setting atime, mtime, access mode and uid/gid, where +errors are being ignored. + +=cut + +sub aio_copy($$;$) { + my ($src, $dst, $cb) = @_; + + my $pri = aioreq_pri; + my $grp = aio_group $cb; + + aioreq_pri $pri; + add $grp aio_open $src, O_RDONLY, 0, sub { + if (my $src_fh = $_[0]) { + my @stat = stat $src_fh; + + aioreq_pri $pri; + add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { + if (my $dst_fh = $_[0]) { + aioreq_pri $pri; + add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { + if ($_[0] == $stat[7]) { + $grp->result (0); + close $src_fh; + + # those should not normally block. should. should. + utime $stat[8], $stat[9], $dst; + chmod $stat[2] & 07777, $dst_fh; + chown $stat[4], $stat[5], $dst_fh; + close $dst_fh; + } else { + $grp->result (-1); + close $src_fh; + close $dst_fh; + + aioreq $pri; + add $grp aio_unlink $dst; + } + }; + } else { + $grp->result (-1); + } + }, + + } else { + $grp->result (-1); + } + }; + + $grp +} + +=item aio_move $srcpath, $dstpath, $callback->($status) + +Try to move the I (directories not supported as either source or +destination) from C<$srcpath> to C<$dstpath> and call the callback with +the C<0> (error) or C<-1> ok. + +This is a composite request that tries to rename(2) the file first. If +rename files with C, it copies the file with C and, if +that is successful, unlinking the C<$srcpath>. + +=cut + +sub aio_move($$;$) { + my ($src, $dst, $cb) = @_; + + my $pri = aioreq_pri; + my $grp = aio_group $cb; + + aioreq_pri $pri; + add $grp aio_rename $src, $dst, sub { + if ($_[0] && $! == EXDEV) { + aioreq_pri $pri; + add $grp aio_copy $src, $dst, sub { + $grp->result ($_[0]); + + if (!$_[0]) { + aioreq_pri $pri; + add $grp aio_unlink $src; + } + }; + } else { + $grp->result ($_[0]); + } + }; + + $grp +} + =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) Scans a directory (similar to C) but additionally tries to @@ -435,7 +496,7 @@ C is a composite request that creates of many sub requests_ C<$maxreq> specifies the maximum number of outstanding aio requests that this function generates. If it is C<< <= 0 >>, then a suitable default -will be chosen (currently 6). +will be chosen (currently 4). On error, the callback is called without arguments, otherwise it receives two array-refs with path-relative entry names. @@ -482,22 +543,27 @@ sub aio_scandir($$$) { my ($path, $maxreq, $cb) = @_; + my $pri = aioreq_pri; + my $grp = aio_group $cb; - $maxreq = 6 if $maxreq <= 0; + $maxreq = 4 if $maxreq <= 0; # stat once + aioreq_pri $pri; add $grp aio_stat $path, sub { return $grp->result () if $_[0]; my $now = time; my $hash1 = join ":", (stat _)[0,1,3,7,9]; # read the directory entries + aioreq_pri $pri; add $grp aio_readdir $path, sub { my $entries = shift or return $grp->result (); # stat the dir another time + aioreq_pri $pri; add $grp aio_stat $path, sub { my $hash2 = join ":", (stat _)[0,1,3,7,9]; @@ -531,11 +597,13 @@ return unless @$entries; my $entry = pop @$entries; + aioreq_pri $pri; add $statgrp aio_stat "$path/$entry/.", sub { if ($_[0] < 0) { push @nondirs, $entry; } else { # need to check for real directory + aioreq_pri $pri; add $statgrp aio_lstat "$path/$entry", sub { if (-d _) { push @dirs, $entry; @@ -716,7 +784,21 @@ =item $grp->result (...) Set the result value(s) that will be passed to the group callback when all -subrequests have finished. By default, no argument will be passed. +subrequests have finished and set thre groups errno to the current value +of errno (just like calling C without an error number). By default, +no argument will be passed and errno is zero. + +=item $grp->errno ([$errno]) + +Sets the group errno value to C<$errno>, or the current value of errno +when the argument is missing. + +Every aio request has an associated errno value that is restored when +the callback is invoked. This method lets you change this value from its +default (0). + +Calling C will also set errno, so make sure you either set C<$!> +before the call to C, or call c after it. =item feed $grp $callback->($grp) @@ -782,6 +864,9 @@ regularly. Returns the number of events processed. Returns immediately when no events are outstanding. +If not all requests were processed for whatever reason, the filehandle +will still be ready when C returns. + Example: Install an Event watcher that automatically calls IO::AIO::poll_cb with high priority: @@ -789,6 +874,22 @@ poll => 'r', async => 1, cb => \&IO::AIO::poll_cb); +=item IO::AIO::poll_some $max_requests + +Similar to C, but only processes up to C<$max_requests> requests +at a time. + +Useful if you want to ensure some level of interactiveness when perl is +not fast enough to process all requests in time. + +Example: Install an Event watcher that automatically calls +IO::AIO::poll_some with low priority, to ensure that other parts of the +program get the CPU sometimes even under high AIO load. + + Event->io (fd => IO::AIO::poll_fileno, + poll => 'r', nice => 1, + cb => sub { IO::AIO::poll_some 256 }); + =item IO::AIO::poll_wait Wait till the result filehandle becomes ready for reading (simply does a @@ -799,14 +900,24 @@ =item IO::AIO::nreqs -Returns the number of requests currently outstanding (i.e. for which their -callback has not been invoked yet). +Returns the number of requests currently in the ready, execute or pending +states (i.e. for which their callback has not been invoked yet). Example: wait till there are no outstanding requests anymore: IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; +=item IO::AIO::nready + +Returns the number of requests currently in the ready state (not yet +executed). + +=item IO::AIO::npending + +Returns the number of requests currently in the pending state (executed, +but not yet processed by poll_cb). + =item IO::AIO::flush Wait till all outstanding AIO requests have been handled. @@ -857,24 +968,23 @@ Under normal circumstances you don't need to call this function. -=item $oldnreqs = IO::AIO::max_outstanding $nreqs - -[REMOVED] - -Pre-2.x versions used max_outstanding for a crude request queue length limit. - -In 2.x+ you are advised to use a group and a feeder to limit -concurrency. The max_outstanding feature ran very unstable (endless -recursions causing segfaults, bad interaction with groups etc.) and was -removed. +=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs -I am deeply sorry, but I am still on the hunt for a good limiting interface. - -Original description was as follows: - -Sets the maximum number of outstanding requests to C<$nreqs>. If you try -to queue up more than this number of requests, the caller will block until -some requests have been handled. +This is a very bad function to use in interactive programs because it +blocks, and a bad way to reduce concurrency because it is inexact: Better +use an C together with a feed callback. + +Sets the maximum number of outstanding requests to C<$nreqs>. If you +to queue up more than this number of requests, the next call to the +C (and C and other functions calling C) +function will block until the limit is no longer exceeded. + +The default value is very large, so there is no practical limit on the +number of outstanding requests. + +You can still queue as many requests as you want. Therefore, +C is mainly useful in simple scripts (with low values) or +as a stop gap to shield against fatal memory overflow (with large values). =back @@ -899,8 +1009,9 @@ min_parallel 8; END { - max_parallel 0; -} + min_parallel 1; + flush; +}; 1;