--- IO-AIO/AIO.pm 2006/10/21 23:06:04 1.52 +++ IO-AIO/AIO.pm 2006/10/22 13:52:11 1.61 @@ -17,33 +17,36 @@ $_[0] > 0 or die "read error: $!"; }; - use IO::AIO 2; # version has aio objects + # version 2+ has request and group objects + use IO::AIO 2; my $req = aio_unlink "/tmp/file", sub { }; $req->cancel; # cancel request if still in queue - # AnyEvent + my $grp = aio_group sub { print "all stats done\n" }; + add $grp aio_stat "..." for ...; + + # AnyEvent integration open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); - # Event + # Event integration Event->io (fd => IO::AIO::poll_fileno, poll => 'r', cb => \&IO::AIO::poll_cb); - # Glib/Gtk2 + # Glib/Gtk2 integration add_watch Glib::IO IO::AIO::poll_fileno, in => sub { IO::AIO::poll_cb; 1 }; - # Tk + # Tk integration Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", readable => \&IO::AIO::poll_cb); - # Danga::Socket + # Danga::Socket integration Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => \&IO::AIO::poll_cb); - =head1 DESCRIPTION This module implements asynchronous I/O using whatever means your @@ -73,13 +76,16 @@ use base 'Exporter'; BEGIN { - our $VERSION = '1.8'; + our $VERSION = '2.0'; 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_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move + aio_group); our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); + @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; + require XSLoader; XSLoader::load ("IO::AIO", $VERSION); } @@ -99,9 +105,8 @@ All functions expecting a filehandle keep a copy of the filehandle internally until the request has finished. -All non-composite requests (requests that are not broken down into -multiple requests) return objects of type L that allow -further manipulation of running requests. +All requests return objects of type L that allow further +manipulation of those requests while they are in-flight. The pathnames you pass to these routines I be absolute and encoded in byte form. The reason for the former is that at the time the @@ -179,6 +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. @@ -198,15 +205,17 @@ sub aio_move($$$) { my ($src, $dst, $cb) = @_; - aio_rename $src, $dst, sub { + my $grp = aio_group $cb; + + add $grp aio_rename $src, $dst, sub { if ($_[0] && $! == EXDEV) { - aio_open $src, O_RDONLY, 0, sub { + add $grp aio_open $src, O_RDONLY, 0, sub { if (my $src_fh = $_[0]) { my @stat = stat $src_fh; - aio_open $dst, O_WRONLY, 0200, sub { + add $grp aio_open $dst, O_WRONLY, 0200, sub { if (my $dst_fh = $_[0]) { - aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { + add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { close $src_fh; if ($_[0] == $stat[7]) { @@ -215,30 +224,32 @@ chown $stat[4], $stat[5], $dst_fh; close $dst_fh; - aio_unlink $src, sub { - $cb->($_[0]); + add $grp aio_unlink $src, sub { + $grp->result ($_[0]); }; } else { my $errno = $!; - aio_unlink $dst, sub { + 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]); } }; + + $grp } =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) @@ -336,15 +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. @@ -391,21 +404,23 @@ sub aio_scandir($$$) { my ($path, $maxreq, $cb) = @_; - $maxreq = 8 if $maxreq <= 0; + my $grp = aio_group $cb; + + $maxreq = 6 if $maxreq <= 0; # stat once - aio_stat $path, sub { - return $cb->() if $_[0]; + 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 - aio_readdir $path, sub { + add $grp aio_readdir $path, sub { my $entries = shift - or return $cb->(); + or return $grp->result (); # stat the dir another time - aio_stat $path, sub { + add $grp aio_stat $path, sub { my $hash2 = join ":", (stat _)[0,1,3,7,9]; my $ndirs; @@ -417,7 +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 ([], $entries); } # sort into likely dirs and likely nondirs @@ -432,19 +447,21 @@ my ($statcb, $schedcb); my $nreq = 0; + my $statgrp = add $grp aio_group; + $schedcb = sub { if (@$entries) { if ($nreq < $maxreq) { my $ent = pop @$entries; $nreq++; - aio_stat "$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); } }; $statcb = sub { @@ -456,7 +473,7 @@ &$schedcb; } else { # need to check for real directory - aio_lstat "$path/$entry", sub { + add $grp aio_lstat "$path/$entry", sub { $nreq--; if (-d _) { @@ -479,6 +496,8 @@ }; }; }; + + $grp } =item aio_fsync $fh, $callback->($status) @@ -494,9 +513,41 @@ 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->(...) + +[EXPERIMENTAL] + +This is a very special aio request: Instead of doing something, it is a +container for other aio requests, which is useful if you want to bundle +many requests into a single, composite, request. + +Returns an object of class L. See its documentation below +for more info. + +Example: + + my $grp = aio_group sub { + print "all stats done\n"; + }; + + add $grp + (aio_stat ...), + (aio_stat ...), + ...; + +=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* + +Mainly used for debugging and benchmarking, this aio request puts one of +the request workers to sleep for the given time. + +While it is theoretically handy to have simple I/O scheduling requests +like sleep and file handle readable/writable, the overhead this creates +is immense, so do not use this function except to put your application +under artificial I/O pressure. + =back -=head2 IO::AIO::CB CLASS +=head2 IO::AIO::REQ CLASS All non-aggregate C functions return an object of this class when called in non-void context. @@ -521,6 +572,124 @@ =back +=head2 IO::AIO::GRP CLASS + +This class is a subclass of L, so all its methods apply to +objects of this class, too. + +A IO::AIO::GRP object is a special request that can contain multiple other +aio requests. + +You create one by calling the C constructing function with a +callback that will be called when all contained requests have entered the +C state: + + my $grp = aio_group sub { + print "all requests are done\n"; + }; + +You add requests by calling the C method with one or more +C objects: + + $grp->add (aio_unlink "..."); + + 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 +C, just like any other request. + +They can be canceled like any other request. Canceling will cancel not +only the request itself, but also all requests it contains. + +They can also can also be added to other IO::AIO::GRP objects. + +You must not add requests to a group from within the group callback (or +any later time). + +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 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 + =head2 SUPPORT FUNCTIONS =over 4 @@ -585,17 +754,18 @@ =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<$nthreads>. The current +default is C<8>, which means eight asynchronous operations can execute +concurrently at any one time (the number of outstanding requests, +however, is unlimited). IO::AIO starts threads only on demand, when an AIO request is queued and no free thread exists. -It is recommended to keep the number of threads low, as some Linux -kernel versions will scale negatively with the number of threads (higher -parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 -threads should be fine. +It is recommended to keep the number of threads relatively low, as some +Linux kernel versions will scale negatively with the number of threads +(higher parallelity => MUCH higher latency). With current Linux 2.6 +versions, 4-32 threads should be fine. Under most circumstances you don't need to call this function, as the module selects a default that is suitable for low to moderate load. @@ -646,7 +816,7 @@ *$sym } -min_parallel 4; +min_parallel 8; END { max_parallel 0; @@ -670,6 +840,19 @@ 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).