--- IO-AIO/AIO.pm 2006/10/22 00:53:47 1.56 +++ IO-AIO/AIO.pm 2006/10/23 00:34:36 1.63 @@ -81,7 +81,7 @@ our @EXPORT = 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_group aio_nop); our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; @@ -184,6 +184,8 @@ =item aio_move $srcpath, $dstpath, $callback->($status) +[EXPERIMENTAL due to internal aio_group use] + 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. @@ -203,7 +205,7 @@ sub aio_move($$$) { my ($src, $dst, $cb) = @_; - my $grp = aio_group; + my $grp = aio_group $cb; add $grp aio_rename $src, $dst, sub { if ($_[0] && $! == EXDEV) { @@ -223,27 +225,27 @@ close $dst_fh; add $grp aio_unlink $src, sub { - $cb->($_[0]); + $grp->result ($_[0]); }; } else { my $errno = $!; add $grp aio_unlink $dst, sub { $! = $errno; - $cb->(-1); + $grp->result (-1); }; } }; } else { - $cb->(-1); + $grp->result (-1); } }, } else { - $cb->(-1); + $grp->result (-1); } }; } else { - $cb->($_[0]); + $grp->result ($_[0]); } }; @@ -345,15 +347,17 @@ =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) +[EXPERIMENTAL due to internal aio_group use] + Scans a directory (similar to C) but additionally tries to separate the entries of directory C<$path> into two sets of names, ones you can recurse into (directories or links to them), and ones you cannot recurse into (everything else). -C is a composite request that consists of many sub -requests. C<$maxreq> specifies the maximum number of outstanding aio -requests that this function generates. If it is C<< <= 0 >>, then a -suitable default will be chosen (currently 8). +C is a composite request that creates of many sub requests_ +C<$maxreq> specifies the maximum number of outstanding aio requests that +this function generates. If it is C<< <= 0 >>, then a suitable default +will be chosen (currently 6). On error, the callback is called without arguments, otherwise it receives two array-refs with path-relative entry names. @@ -400,20 +404,20 @@ sub aio_scandir($$$) { my ($path, $maxreq, $cb) = @_; - my $grp = aio_group; + my $grp = aio_group $cb; - $maxreq = 8 if $maxreq <= 0; + $maxreq = 6 if $maxreq <= 0; # stat once add $grp aio_stat $path, sub { - return $cb->() if $_[0]; + return $grp->result () if $_[0]; my $now = time; my $hash1 = join ":", (stat _)[0,1,3,7,9]; # read the directory entries add $grp aio_readdir $path, sub { my $entries = shift - or return $cb->(); + or return $grp->result (); # stat the dir another time add $grp aio_stat $path, sub { @@ -428,7 +432,7 @@ # if nlink == 2, we are finished # on non-posix-fs's, we rely on nlink < 2 $ndirs = (stat _)[3] - 2 - or return $cb->([], $entries); + or return $grp->result ([], $entries); } # sort into likely dirs and likely nondirs @@ -443,19 +447,21 @@ my ($statcb, $schedcb); my $nreq = 0; + my $statgrp = add $grp aio_group; + $schedcb = sub { if (@$entries) { if ($nreq < $maxreq) { my $ent = pop @$entries; $nreq++; - add $grp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; + add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; } } elsif (!$nreq) { # finished + $statgrp->cancel; undef $statcb; undef $schedcb; - $cb->(\@dirs, \@nondirs) if $cb; - undef $cb; + $grp->result (\@dirs, \@nondirs); } }; $statcb = sub { @@ -507,7 +513,7 @@ If this call isn't available because your OS lacks it or it couldn't be detected, it will be emulated by calling C instead. -=item aio_group $callback->() +=item aio_group $callback->(...) [EXPERIMENTAL] @@ -529,6 +535,13 @@ (aio_stat ...), ...; +=item aio_nop $callback->() + +This is a special request - it does nothing in itself and is only used for +side effects, such as when you want to add a dummy request to a group so +that finishing the requests in the group depends on executing the given +code. + =item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* Mainly used for debugging and benchmarking, this aio request puts one of @@ -587,36 +600,108 @@ $grp->add (aio_unlink "..."); - add $grp aio_stat "...", sub { ... }; + add $grp aio_stat "...", sub { + $_[0] or return $grp->result ("error"); + + # add another request dynamically, if first succeeded + add $grp aio_open "...", sub { + $grp->result ("ok"); + }; + }; This makes it very easy to create composite requests (see the source of C for an application) that work and feel like simple requests. -The IO::AIO::GRP objects will be cleaned up during calls to +=over 4 + +=item * The IO::AIO::GRP objects will be cleaned up during calls to C, just like any other request. -They can be canceled like any other request. Canceling will cancel not -just the request itself, but also all requests it contains. +=item * They can be canceled like any other request. Canceling will cancel not +only the request itself, but also all requests it contains. + +=item * They can also can also be added to other IO::AIO::GRP objects. -They can also can also be added to other IO::AIO::GRP objects. +=item * You must not add requests to a group from within the group callback (or +any later time). + +=item * This does not harmonise well with C, so best do +not combine C with it. Groups and feeders are recommended for +this kind of concurrency-limiting. + +=back Their lifetime, simplified, looks like this: when they are empty, they will finish very quickly. If they contain only requests that are in the C state, they will also finish. Otherwise they will continue to exist. +That means after creating a group you have some time to add requests. And +in the callbacks of those requests, you can add further requests to the +group. And only when all those requests have finished will the the group +itself finish. + =over 4 =item $grp->add (...) =item add $grp ... -Add one or more -Cancels the request, if possible. Has the effect of skipping execution -when entering the B state and skipping calling the callback when -entering the the B state, but will leave the request otherwise -untouched. That means that requests that currently execute will not be -stopped and resources held by the request will not be freed prematurely. +Add one or more requests to the group. Any type of L can +be added, including other groups, as long as you do not create circular +dependencies. + +Returns all its arguments. + +=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. + +=item $grp->set_feeder ($callback->($grp)) + +[VERY EXPERIMENTAL] + +Sets a feeder/generator on this group: every group can have an attached +generator that generates requests if idle. The idea behind this is that, +although you could just queue as many requests as you want in a group, +this might starve other requests for a potentially long time. For +example, C might generate hundreds of thousands C +requests, delaying any later requests for a long time. + +To avoid this, and allow incremental generation of requests, you can +instead a group and set a feeder on it that generates those requests. The +feeder will be called whenever there are few enough (see C, +below) requests active in the group itself and is expected to queue more +requests. + +The feeder can queue as many requests as it likes (i.e. C does not +impose any limits). + +If the feeder does not queue more requests when called, it will be +automatically removed from the group. + +If the feeder limit is C<0>, it will be set to C<2> automatically. + +Example: + + # stat all files in @files, but only ever use four aio requests concurrently: + + my $grp = aio_group sub { print "finished\n" }; + $grp->feeder_limit (4); + $grp->set_feeder (sub { + my $file = pop @files + or return; + + add $grp aio_stat $file, sub { ... }; + }); + +=item $grp->feeder_limit ($num) + +Sets the feeder limit for the group: The feeder will be called whenever +the group contains less than this many requests. + +Setting the limit to C<0> will pause the feeding process. =back @@ -684,17 +769,18 @@ =item IO::AIO::min_parallel $nthreads -Set the minimum number of AIO threads to C<$nthreads>. The current default -is C<4>, which means four asynchronous operations can be done at one time -(the number of outstanding operations, however, is unlimited). +Set the minimum number of AIO threads to C<$nthreads>. The current +default is C<8>, which means eight asynchronous operations can execute +concurrently at any one time (the number of outstanding requests, +however, is unlimited). IO::AIO starts threads only on demand, when an AIO request is queued and no free thread exists. -It is recommended to keep the number of threads low, as some Linux -kernel versions will scale negatively with the number of threads (higher -parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 -threads should be fine. +It is recommended to keep the number of threads relatively low, as some +Linux kernel versions will scale negatively with the number of threads +(higher parallelity => MUCH higher latency). With current Linux 2.6 +versions, 4-32 threads should be fine. Under most circumstances you don't need to call this function, as the module selects a default that is suitable for low to moderate load. @@ -715,6 +801,8 @@ =item $oldnreqs = IO::AIO::max_outstanding $nreqs +[DEPRECATED] + Sets the maximum number of outstanding requests to C<$nreqs>. If you try to queue up more than this number of requests, the caller will block until some requests have been handled. @@ -723,6 +811,10 @@ queue up many requests in a loop it often improves speed if you set this to a relatively low number, such as C<100>. +This function does not work well together with C's, and their +feeder interface is better suited to limiting concurrency, so do not use +this function. + Under normal circumstances you don't need to call this function. =back @@ -745,7 +837,7 @@ *$sym } -min_parallel 4; +min_parallel 8; END { max_parallel 0; @@ -769,6 +861,19 @@ not been called, while the child will act as if IO::AIO has not been used yet. +=head2 MEMORY USAGE + +Each aio request uses - depending on your architecture - around 128 bytes +of memory. In addition, stat requests need a stat buffer (possibly a few +hundred bytes). Perl scalars and other data passed into aio requests will +also be locked. + +This is now awfully much, so queuing lots of requests is not usually a +problem. + +Each thread needs a stack area which is usually around 16k, sometimes much +larger, depending on the OS. + =head1 SEE ALSO L, L (obsolete).