[ViewVC] Diff of: cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.51 by root, Sat Jun 24 19:14:04 2006 UTC vs.
Revision 1.59 by root, Sun Oct 22 10:33:26 2006 UTC

  aio_read $fh, 30000, 1024, $buffer, 0, sub {
     $_[0] > 0 or die "read error: $!";
  };
- # AnyEvent
+ # 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
+ # 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
 operating system supports.
 use strict 'vars';
 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);
 }
 perl, which usually delivers "false") as it's sole argument when the given
 syscall has been executed asynchronously.
 All functions expecting a filehandle keep a copy of the filehandle
 internally until the request has finished.
+All requests return objects of type L<IO::AIO::REQ> that allow further
+manipulation of those requests while they are in-flight.
 The pathnames you pass to these routines I<must> 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
 changed. Alternatively, you can make sure that you never change the
       print "read $_[0] bytes: <$buffer>\n";
    };
 =item aio_move $srcpath, $dstpath, $callback->($status)
-[EXPERIMENTAL]
+[EXPERIMENTAL due to internal aio_group use]
-Try to move the I<file> (directories not supported as either source or destination)
+Try to move the I<file> (directories not supported as either source or
-from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok.
+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<EXDEV>, it creates the destination file with mode 0200
 and copies the contents of the source file into it using C<aio_sendfile>,
 followed by restoring atime, mtime, access mode and uid/gid, in that
 =cut
 sub aio_move($$$) {
    my ($src, $dst, $cb) = @_;
+   my $grp = aio_group $cb;
-   aio_rename $src, $dst, sub {
+   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]) {
                            utime $stat[8], $stat[9], $dst;
                            chmod $stat[2] & 07777, $dst_fh;
                            chown $stat[4], $stat[5], $dst_fh;
                            close $dst_fh;
-                           aio_unlink $src, sub {
+                           add $grp aio_unlink $src, sub {
-                              $cb->($_[0]);
+                              $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)
 Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
 The callback a single argument which is either C<undef> or an array-ref
 with the filenames.
 =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
+[EXPERIMENTAL due to internal aio_group use]
-Scans a directory (similar to C<aio_readdir>) and tries to separate the
+Scans a directory (similar to C<aio_readdir>) but additionally tries to
-entries of directory C<$path> into two sets of names, ones you can recurse
+separate the entries of directory C<$path> into two sets of names, ones
-into (directories), and ones you cannot recurse into (everything else).
+you can recurse into (directories or links to them), and ones you cannot
+recurse into (everything else).
-C<aio_scandir> is a composite request that consists of many
+C<aio_scandir> is a composite request that consists of many sub
-aio-primitives. C<$maxreq> specifies the maximum number of outstanding
+requests. C<$maxreq> specifies the maximum number of outstanding aio
-aio requests that this function generates. If it is C<< <= 0 >>, then a
+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
 two array-refs with path-relative entry names.
 Implementation notes.
 The C<aio_readdir> cannot be avoided, but C<stat()>'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
+directory before and after the readdir is checked, and if they match (and
-link count will be used to decide how many entries are directories (if
+isn't the current time), the link count will be used to decide how many
->= 2). Otherwise, no knowledge of the number of subdirectories will be
+entries are directories (if >= 2). Otherwise, no knowledge of the number
-assumed.
+of subdirectories will be assumed.
-Then entires will be sorted into likely directories (everything without a
+Then entries will be sorted into likely directories (everything without
-non-initial dot) and likely non-directories (everything else).  Then every
+a non-initial dot currently) and likely non-directories (everything
-entry + C</.> will be C<stat>'ed, likely directories first. This is often
+else). Then every entry plus an appended C</.> will be C<stat>'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
-faster because filesystems might detect the type of the entry without
+filesystems might detect the type of the entry without reading the inode
-reading the inode data (e.g. ext2fs filetype feature). If that succeeds,
+data (e.g. ext2fs filetype feature).
-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
+If the known number of directories (link count - 2) has been reached, the
-entries is assumed to be non-directories.
+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 {
+   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
-      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 return $cb->([], $entries);
+                  or return $grp->result ([], $entries);
             }
             # sort into likely dirs and likely nondirs
             # dirs == files without ".", short entries first
             $entries = [map $_->[0],
             $schedcb = sub {
                if (@$entries) {
                   if ($nreq < $maxreq) {
                      my $ent = pop @$entries;
                      $nreq++;
-                     aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
+                     add $grp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
                   }
                } elsif (!$nreq) {
                   # finished
                   undef $statcb;
                   undef $schedcb;
-                  $cb->(\@dirs, \@nondirs) if $cb;
+                  $grp->result (\@dirs, \@nondirs) if $cb;
                   undef $cb;
                }
             };
             $statcb = sub {
                my ($status, $entry) = @_;
                   $nreq--;
                   push @nondirs, $entry;
                   &$schedcb;
                } else {
                   # need to check for real directory
-                  aio_lstat "$path/$entry", sub {
+                  add $grp aio_lstat "$path/$entry", sub {
                      $nreq--;
                      if (-d _) {
                         push @dirs, $entry;
             &$schedcb while @$entries && $nreq < $maxreq;
          };
       };
    };
+   $grp
 }
 =item aio_fsync $fh, $callback->($status)
 Asynchronously call fsync on the given filehandle and call the callback
 Asynchronously call fdatasync on the given filehandle and call the
 callback with the fdatasync result code.
 If this call isn't available because your OS lacks it or it couldn't be
 detected, it will be emulated by calling C<fsync> 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<IO::AIO::GRP>. 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<aio_*> 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<ready> (request has been created, but has not been executed
+yet), B<execute> (request is currently being executed), B<pending>
+(request has been executed but callback has not been called yet),
+B<result> (results are being processed synchronously, includes calling the
+callback) and B<done> (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<execute> state and skipping calling the callback when
+entering the the B<result> 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<IO::AIO::REQ>, 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<aio_group> constructing function with a
+callback that will be called when all contained requests have entered the
+C<done> state:
+   my $grp = aio_group sub {
+      print "all requests are done\n";
+   };
+You add requests by calling the C<add> method with one or more
+C<IO::AIO::REQ> 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<aio_move> for an application) that work and feel like simple requests.
+The IO::AIO::GRP objects will be cleaned up during calls to
+C<IO::AIO::poll_cb>, 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.
+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<done> 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<IO::AIO::REQ> 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.
 =back
 =head2 SUPPORT FUNCTIONS
 }
 1;
 =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.
 =head1 SEE ALSO
-L<Coro>, L<Linux::AIO>.
+L<Coro>, L<Linux::AIO> (obsolete).
 =head1 AUTHOR
  Marc Lehmann <schmorp@schmorp.de>
  http://home.schmorp.de/

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing IO-AIO/AIO.pm (file contents): Revision 1.51 by root, Sat Jun 24 19:14:04 2006 UTC vs. Revision 1.59 by root, Sun Oct 22 10:33:26 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.51 by root, Sat Jun 24 19:14:04 2006 UTC vs.
Revision 1.59 by root, Sun Oct 22 10:33:26 2006 UTC