--- IO-AIO/AIO.pm 2005/09/07 17:41:17 1.41 +++ IO-AIO/AIO.pm 2006/10/22 13:33:28 1.60 @@ -17,24 +17,36 @@ $_[0] > 0 or die "read error: $!"; }; - # Event + # 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 + + 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 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 @@ -59,22 +71,23 @@ package IO::AIO; no warnings; +use strict 'vars'; use base 'Exporter'; -use Fcntl (); - BEGIN { - $VERSION = '1.61'; + 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_group); + our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); - @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); - @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; + XSLoader::load ("IO::AIO", $VERSION); } =head1 FUNCTIONS @@ -92,6 +105,9 @@ All functions expecting a filehandle keep a copy of the filehandle internally until the request has finished. +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 request is being executed, the current working directory could have @@ -166,6 +182,76 @@ print "read $_[0] bytes: <$buffer>\n"; }; +=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. + +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 @@ -230,12 +316,27 @@ Asynchronously unlink (delete) a file and call the callback with the result code. +=item aio_link $srcpath, $dstpath, $callback->($status) + +Asynchronously create a new link to the existing object at C<$srcpath> at +the path C<$dstpath> and call the callback with the result code. + +=item aio_symlink $srcpath, $dstpath, $callback->($status) + +Asynchronously create a new symbolic link to the existing object at C<$srcpath> at +the path C<$dstpath> and call the callback with the result code. + +=item aio_rename $srcpath, $dstpath, $callback->($status) + +Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as +rename(2) and call the callback with the result code. + =item aio_rmdir $pathname, $callback->($status) Asynchronously rmdir (delete) a directory and call the callback with the result code. -=item aio_readdir $pathname $callback->($entries) +=item aio_readdir $pathname, $callback->($entries) Unlike the POSIX call of the same name, C reads an entire directory (i.e. opendir + readdir + closedir). The entries will not be @@ -246,13 +347,16 @@ =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) -Scans a directory (similar to C) and tries to separate the -entries of directory C<$path> into two sets of names, ones you can recurse -into (directories), and ones you cannot recurse into (everything else). - -C is a composite request that consists of many -aio-primitives. C<$maxreq> specifies the maximum number of outstanding -aio requests that this function generates. If it is C<< <= 0 >>, then a +[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). On error, the callback is called without arguments, otherwise it receives @@ -271,53 +375,64 @@ The C cannot be avoided, but C'ing every entry can. After reading the directory, the modification time, size etc. of the -directory before and after the readdir is checked, and if they match, the -link count will be used to decide how many entries are directories (if ->= 2). Otherwise, no knowledge of the number of subdirectories will be -assumed. - -Then entires will be sorted into likely directories (everything without a -non-initial dot) and likely non-directories (everything else). Then every -entry + C will be C'ed, likely directories first. This is often -faster because filesystems might detect the type of the entry without -reading the inode data (e.g. ext2s filetype feature). If that succeeds, -it assumes that the entry is a directory or a symlink to directory (which -will be checked seperately). - -If the known number of directories has been reached, the rest of the -entries is assumed to be non-directories. +directory before and after the readdir is checked, and if they match (and +isn't the current time), the link count will be used to decide how many +entries are directories (if >= 2). Otherwise, no knowledge of the number +of subdirectories will be assumed. + +Then entries will be sorted into likely directories (everything without +a non-initial dot currently) and likely non-directories (everything +else). Then every entry plus an appended C will be C'ed, +likely directories first. If that succeeds, it assumes that the entry +is a directory or a symlink to directory (which will be checked +seperately). This is often faster than stat'ing the entry itself because +filesystems might detect the type of the entry without reading the inode +data (e.g. ext2fs filetype feature). + +If the known number of directories (link count - 2) has been reached, the +rest of the entries is assumed to be non-directories. + +This only works with certainty on POSIX (= UNIX) filesystems, which +fortunately are the vast majority of filesystems around. + +It will also likely work on non-POSIX filesystems with reduced efficiency +as those tend to return 0 or 1 as link counts, which disables the +directory counting heuristic. =cut sub aio_scandir($$$) { my ($path, $maxreq, $cb) = @_; + my $grp = aio_group $cb; + $maxreq = 8 if $maxreq <= 0; # stat once - aio_stat $path, sub { - $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 $ndirs; # take the slow route if anything looks fishy - if ($hash1 ne $hash2) { + if ($hash1 ne $hash2 or (stat _)[9] == $now) { $ndirs = -1; } else { # if nlink == 2, we are finished # on non-posix-fs's, we rely on nlink < 2 $ndirs = (stat _)[3] - 2 - or $cb->([], $entries); + or return $grp->result ([], $entries); } # sort into likely dirs and likely nondirs @@ -332,19 +447,21 @@ my ($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); - undef $cb; + $grp->result (\@dirs, \@nondirs); } }; $statcb = sub { @@ -356,7 +473,7 @@ &$schedcb; } else { # need to check for real directory - aio_lstat "$path/$entry", sub { + add $grp aio_lstat "$path/$entry", sub { $nreq--; if (-d _) { @@ -379,6 +496,8 @@ }; }; }; + + $grp } =item aio_fsync $fh, $callback->($status) @@ -394,6 +513,181 @@ 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::REQ CLASS + +All non-aggregate C functions return an object of this class when +called in non-void context. + +A request always moves through the following five states in its lifetime, +in order: B (request has been created, but has not been executed +yet), B (request is currently being executed), B +(request has been executed but callback has not been called yet), +B (results are being processed synchronously, includes calling the +callback) and B (request has reached the end of its lifetime and +holds no resources anymore). + +=over 4 + +=item $req->cancel + +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. + +=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 @@ -531,17 +825,36 @@ =head2 FORK BEHAVIOUR +This module should do "the right thing" when the process using it forks: + Before the fork, IO::AIO enters a quiescent state where no requests can be added in other threads and no results will be processed. After the fork the parent simply leaves the quiescent state and continues request/result processing, while the child clears the request/result queue (so the requests started before the fork will only be handled in -the parent). Threats will be started on demand until the limit ste in the +the parent). Threads will be started on demand until the limit ste in the parent process has been reached again. +In short: the parent will, after a short pause, continue as if fork had +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. +L, L (obsolete). =head1 AUTHOR