--- IO-AIO/AIO.pm	2006/10/27 20:11:58	1.83
+++ IO-AIO/AIO.pm	2008/10/22 18:15:36	1.142
@@ -7,7 +7,8 @@
  use IO::AIO;
 
  aio_open "/etc/passwd", O_RDONLY, 0, sub {
-    my ($fh) = @_;
+    my $fh = shift
+       or die "/etc/passwd: $!";
     ...
  };
 
@@ -27,9 +28,11 @@
  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 });
+ # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
+ use AnyEvent::AIO;
+
+ # EV integration
+ my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
 
  # Event integration
  Event->io (fd => IO::AIO::poll_fileno,
@@ -53,20 +56,80 @@
 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 most of 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<Event|Event>
+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.
 
-Although the module will work with in the presence of other (Perl-)
-threads, it is currently not reentrant in any way, so use appropriate
-locking yourself, always call C<poll_cb> from within the same thread, or
-never call C<poll_cb> (or other C<aio_> functions) recursively.
+Although the module will work in the presence of other (Perl-) threads,
+it is currently not reentrant in any way, so use appropriate locking
+yourself, always call C<poll_cb> from within the same thread, or never
+call C<poll_cb> (or other C<aio_> functions) recursively.
+
+=head2 EXAMPLE
+
+This is a simple example that uses the Event module and loads
+F</etc/passwd> asynchronously:
+
+   use Fcntl;
+   use Event;
+   use IO::AIO;
+
+   # register the IO::AIO callback with Event
+   Event->io (fd => IO::AIO::poll_fileno,
+              poll => 'r',
+              cb => \&IO::AIO::poll_cb);
+
+   # queue the request to open /etc/passwd
+   aio_open "/etc/passwd", O_RDONLY, 0, sub {
+      my $fh = shift
+         or die "error while opening: $!";
+
+      # stat'ing filehandles is generally non-blocking
+      my $size = -s $fh;
+
+      # queue a request to read the file
+      my $contents;
+      aio_read $fh, 0, $size, $contents, 0, sub {
+         $_[0] == $size
+            or die "short read: $!";
+
+         close $fh;
+
+         # file contents now in $contents
+         print $contents;
+
+         # exit event loop and program
+         Event::unloop;
+      };
+   };
+
+   # possibly queue up other requests, or open GUI windows,
+   # check for sockets etc. etc.
+
+   # process events as long as there are some:
+   Event::loop;
 
 =head1 REQUEST ANATOMY AND LIFETIME
 
@@ -118,25 +181,35 @@
 aio request is severed and calling its methods will either do nothing or
 result in a runtime error).
 
+=back
+
 =cut
 
 package IO::AIO;
 
+use Carp ();
+
 no warnings;
 use strict 'vars';
 
 use base 'Exporter';
 
 BEGIN {
-   our $VERSION = '2.0';
+   our $VERSION = '3.16';
+
+   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_readlink aio_sync aio_fsync
+                     aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
+                     aio_rename aio_link aio_move aio_copy aio_group
+                     aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
+                     aio_chmod aio_utime aio_truncate);
 
-   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_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 nready npending);
+                       min_parallel max_parallel max_idle
+                       nreqs nready npending nthreads
+                       max_poll_time max_poll_reqs);
 
    @IO::AIO::GRP::ISA = 'IO::AIO::REQ';
 
@@ -146,34 +219,38 @@
 
 =head1 FUNCTIONS
 
-=head2 AIO FUNCTIONS
+=head2 AIO REQUEST FUNCTIONS
 
 All the C<aio_*> calls are more or less thin wrappers around the syscall
 with the same name (sans C<aio_>). The arguments are similar or identical,
 and they all accept an additional (and optional) C<$callback> argument
 which must be a code reference. This code reference will get called with
 the syscall return code (e.g. most syscalls return C<-1> on error, unlike
-perl, which usually delivers "false") as it's sole argument when the given
+perl, which usually delivers "false") as its sole argument after 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.
+All functions return request 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
+encoded as octets. 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
-current working directory.
+current working directory anywhere in the program and then use relative
+paths.
 
-To encode pathnames to byte form, either make sure you either: a)
-always pass in filenames you got from outside (command line, readdir
-etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
+To encode pathnames as octets, either make sure you either: a) always pass
+in filenames you got from outside (command line, readdir etc.) without
+tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
 your pathnames to the locale (or other) encoding in effect in the user
 environment, d) use Glib::filename_from_unicode on unicode filenames or e)
-use something else.
+use something else to ensure your scalar has the correct contents.
+
+This works, btw. independent of the internal UTF-8 bit, which IO::AIO
+handles correctly whether it is set or not.
 
 =over 4
 
@@ -203,10 +280,12 @@
       };
    };
 
+
 =item aioreq_nice $pri_adjust
 
 Similar to C<aioreq_pri>, but subtracts the given value from the current
-priority, so effects are cumulative.
+priority, so the effect is cumulative.
+
 
 =item aio_open $pathname, $flags, $mode, $callback->($fh)
 
@@ -222,7 +301,9 @@
 Likewise, C<$mode> specifies the mode of the newly created file, if it
 didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
 except that it is mandatory (i.e. use C<0> if you don't create new files,
-and C<0666> or C<0777> if you do).
+and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
+by the umask in effect then the request is being executed, so better never
+change the umask.
 
 Example:
 
@@ -235,29 +316,45 @@
       }
    };
 
+
 =item aio_close $fh, $callback->($status)
 
 Asynchronously close a file and call the callback with the result
-code. I<WARNING:> although accepted, you should not pass in a perl
-filehandle here, as perl will likely close the file descriptor another
-time when the filehandle is destroyed. Normally, you can safely call perls
-C<close> or just let filehandles go out of scope.
+code.
+
+Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
+closing the file descriptor associated with the filehandle itself.
+
+Therefore, C<aio_close> will not close the filehandle - instead it will
+use dup2 to overwrite the file descriptor with the write-end of a pipe
+(the pipe fd will be created on demand and will be cached).
 
-This is supposed to be a bug in the API, so that might change. It's
-therefore best to avoid this function.
+Or in other words: the file descriptor will be closed, but it will not be
+free for reuse until the perl filehandle is closed.
+
+=cut
 
 =item aio_read  $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
 
 =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
 
-Reads or writes C<length> bytes from the specified C<fh> and C<offset>
-into the scalar given by C<data> and offset C<dataoffset> and calls the
+Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset>
+into the scalar given by C<$data> and offset C<$dataoffset> and calls the
 callback without the actual number of bytes read (or -1 on error, just
 like the syscall).
 
+If C<$offset> is undefined, then the current file descriptor offset will
+be used (and updated), otherwise the file descriptor offset will not be
+changed by these calls.
+
+If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>.
+
+If C<$dataoffset> is less than zero, it will be counted from the end of
+C<$data>.
+
 The C<$data> scalar I<MUST NOT> be modified in any way while the request
-is outstanding. Modifying it can result in segfaults or WW3 (if the
-necessary/optional hardware is installed).
+is outstanding. Modifying it can result in segfaults or World War III (if
+the necessary/optional hardware is installed).
 
 Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
 offset C<0> within the scalar:
@@ -267,6 +364,7 @@
       print "read $_[0] bytes: <$buffer>\n";
    };
 
+
 =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
 
 Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
@@ -290,6 +388,7 @@
 value equals C<$length> one can assume that C<$length> bytes have been
 read.
 
+
 =item aio_readahead $fh,$offset,$length, $callback->($retval)
 
 C<aio_readahead> populates the page cache with data from a file so that
@@ -304,6 +403,7 @@
 If that syscall doesn't exist (likely if your OS isn't Linux) it will be
 emulated by simply reading the data, which would have a similar effect.
 
+
 =item aio_stat  $fh_or_path, $callback->($status)
 
 =item aio_lstat $fh, $callback->($status)
@@ -326,39 +426,103 @@
       print "size is ", -s _, "\n";
    };
 
+
+=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
+
+Works like perl's C<utime> function (including the special case of $atime
+and $mtime being undef). Fractional times are supported if the underlying
+syscalls support them.
+
+When called with a pathname, uses utimes(2) if available, otherwise
+utime(2). If called on a file descriptor, uses futimes(2) if available,
+otherwise returns ENOSYS, so this is not portable.
+
+Examples:
+
+   # set atime and mtime to current time (basically touch(1)):
+   aio_utime "path", undef, undef;
+   # set atime to current time and mtime to beginning of the epoch:
+   aio_utime "path", time, undef; # undef==0
+
+
+=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
+
+Works like perl's C<chown> function, except that C<undef> for either $uid
+or $gid is being interpreted as "do not change" (but -1 can also be used).
+
+Examples:
+
+   # same as "chown root path" in the shell:
+   aio_chown "path", 0, -1;
+   # same as above:
+   aio_chown "path", 0, undef;
+
+
+=item aio_truncate $fh_or_path, $offset, $callback->($status)
+
+Works like truncate(2) or ftruncate(2).
+
+
+=item aio_chmod $fh_or_path, $mode, $callback->($status)
+
+Works like perl's C<chmod> function.
+
+
 =item aio_unlink $pathname, $callback->($status)
 
 Asynchronously unlink (delete) a file and call the callback with the
 result code.
 
+
 =item aio_mknod $path, $mode, $dev, $callback->($status)
 
+[EXPERIMENTAL]
+
 Asynchronously create a device node (or fifo). See mknod(2).
 
-The only portable (POSIX) way of calling this function is:
+The only (POSIX-) portable 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<$srcpath> at
 the path C<$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_readlink $path, $callback->($link)
+
+Asynchronously read the symlink specified by C<$path> and pass it to
+the callback. If an error occurs, nothing or undef gets passed to the
+callback.
+
+
 =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_mkdir $pathname, $mode, $callback->($status)
+
+Asynchronously mkdir (create) a directory and call the callback with
+the result code. C<$mode> will be modified by the umask at the time the
+request is executed, so do not change your umask.
+
+
 =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)
 
 Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
@@ -368,13 +532,42 @@
 The callback a single argument which is either C<undef> or an array-ref
 with the filenames.
 
+
+=item aio_load $path, $data, $callback->($status)
+
+This is a composite request that tries to fully load the given file into
+memory. Status is the same as with aio_read.
+
+=cut
+
+sub aio_load($$;$) {
+   my ($path, undef, $cb) = @_;
+   my $data = \$_[1];
+
+   my $pri = aioreq_pri;
+   my $grp = aio_group $cb;
+
+   aioreq_pri $pri;
+   add $grp aio_open $path, O_RDONLY, 0, sub {
+      my $fh = shift
+         or return $grp->result (-1);
+
+      aioreq_pri $pri;
+      add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
+         $grp->result ($_[0]);
+      };
+   };
+
+   $grp
+}
+
 =item aio_copy $srcpath, $dstpath, $callback->($status)
 
 Try to copy the I<file> (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
+This is a composite request that 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 order.
@@ -409,7 +602,9 @@
                      utime $stat[8], $stat[9], $dst;
                      chmod $stat[2] & 07777, $dst_fh;
                      chown $stat[4], $stat[5], $dst_fh;
-                     close $dst_fh;
+
+                     aioreq_pri $pri;
+                     add $grp aio_close $dst_fh;
                   } else {
                      $grp->result (-1);
                      close $src_fh;
@@ -438,9 +633,9 @@
 destination) from C<$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 copies the file with C<aio_copy> and, if
-that is successful, unlinking the C<$srcpath>.
+This is a composite request that tries to rename(2) the file first; if
+rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
+that is successful, unlinks the C<$srcpath>.
 
 =cut
 
@@ -524,7 +719,7 @@
 
 =cut
 
-sub aio_scandir($$$) {
+sub aio_scandir($$;$) {
    my ($path, $maxreq, $cb) = @_;
 
    my $pri = aioreq_pri;
@@ -610,6 +805,45 @@
    $grp
 }
 
+=item aio_rmtree $path, $callback->($status)
+
+Delete a directory tree starting (and including) C<$path>, return the
+status of the final C<rmdir> only.  This is a composite request that
+uses C<aio_scandir> to recurse into and rmdir directories, and unlink
+everything else.
+
+=cut
+
+sub aio_rmtree;
+sub aio_rmtree($;$) {
+   my ($path, $cb) = @_;
+
+   my $pri = aioreq_pri;
+   my $grp = aio_group $cb;
+
+   aioreq_pri $pri;
+   add $grp aio_scandir $path, 0, sub {
+      my ($dirs, $nondirs) = @_;
+
+      my $dirgrp = aio_group sub {
+         add $grp aio_rmdir $path, sub {
+            $grp->result ($_[0]);
+         };
+      };
+
+      (aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
+      (aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
+
+      add $grp $dirgrp;
+   };
+
+   $grp
+}
+
+=item aio_sync $callback->($status)
+
+Asynchronously call sync and call the callback when finished.
+
 =item aio_fsync $fh, $callback->($status)
 
 Asynchronously call fsync on the given filehandle and call the callback
@@ -623,6 +857,56 @@
 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_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
+
+Sync the data portion of the file specified by C<$offset> and C<$length>
+to disk (but NOT the metadata), by calling the Linux-specific
+sync_file_range call. If sync_file_range is not available or it returns
+ENOSYS, then fdatasync or fsync is being substituted.
+
+C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
+C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
+C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
+manpage for details.
+
+=item aio_pathsync $path, $callback->($status)
+
+This request tries to open, fsync and close the given path. This is a
+composite request intended to sync directories after directory operations
+(E.g. rename). This might not work on all operating systems or have any
+specific effect, but usually it makes sure that directory changes get
+written to disc. It works for anything that can be opened for read-only,
+not just directories.
+
+Passes C<0> when everything went ok, and C<-1> on error.
+
+=cut
+
+sub aio_pathsync($;$) {
+   my ($path, $cb) = @_;
+
+   my $pri = aioreq_pri;
+   my $grp = aio_group $cb;
+
+   aioreq_pri $pri;
+   add $grp aio_open $path, O_RDONLY, 0, sub {
+      my ($fh) = @_;
+      if ($fh) {
+         aioreq_pri $pri;
+         add $grp aio_fsync $fh, sub {
+            $grp->result ($_[0]);
+
+            aioreq_pri $pri;
+            add $grp aio_close $fh;
+         };
+      } else {
+         $grp->result (-1);
+      }
+   };
+
+   $grp
+}
+
 =item aio_group $callback->(...)
 
 This is a very special aio request: Instead of doing something, it is a
@@ -743,10 +1027,11 @@
 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.
+That means after creating a group you have some time to add requests
+(precisely before the callback has been invoked, which is only done within
+the C<poll_cb>). 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
 
@@ -768,7 +1053,7 @@
 =item $grp->result (...)
 
 Set the result value(s) that will be passed to the group callback when all
-subrequests have finished and set thre groups errno to the current value
+subrequests have finished and set the groups errno to the current value
 of errno (just like calling C<errno> without an error number). By default,
 no argument will be passed and errno is zero.
 
@@ -789,9 +1074,9 @@
 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<aio_scandir> might generate hundreds of thousands C<aio_stat>
-requests, delaying any later requests for a long time.
+this might starve other requests for a potentially long time. For example,
+C<aio_scandir> might generate hundreds of thousands C<aio_stat> 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
@@ -805,7 +1090,8 @@
 If the feed does not queue more requests when called, it will be
 automatically removed from the group.
 
-If the feed limit is C<0>, it will be set to C<2> automatically.
+If the feed limit is C<0> when this method is called, it will be set to
+C<2> automatically.
 
 Example:
 
@@ -827,10 +1113,15 @@
 
 Setting the limit to C<0> will pause the feeding process.
 
+The default value for the limit is C<0>, but note that setting a feeder
+automatically bumps it up to C<2>.
+
 =back
 
 =head2 SUPPORT FUNCTIONS
 
+=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
+
 =over 4
 
 =item $fileno = IO::AIO::poll_fileno
@@ -844,12 +1135,15 @@
 
 =item IO::AIO::poll_cb
 
-Process all outstanding events on the result pipe. You have to call this
-regularly. Returns the number of events processed. Returns immediately
-when no events are outstanding.
+Process some outstanding events on the result pipe. You have to call this
+regularly. Returns C<0> if all events could be processed, or C<-1> if it
+returned earlier for whatever reason. Returns immediately when no events
+are outstanding. The amount of events processed depends on the settings of
+C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
 
 If not all requests were processed for whatever reason, the filehandle
-will still be ready when C<poll_cb> returns.
+will still be ready when C<poll_cb> returns, so normally you don't have to
+do anything special to have it called later.
 
 Example: Install an Event watcher that automatically calls
 IO::AIO::poll_cb with high priority:
@@ -858,49 +1152,56 @@
               poll => 'r', async => 1,
               cb => \&IO::AIO::poll_cb);
 
-=item IO::AIO::poll_some $max_requests
+=item IO::AIO::max_poll_reqs $nreqs
+
+=item IO::AIO::max_poll_time $seconds
 
-Similar to C<poll_cb>, but only processes up to C<$max_requests> requests
-at a time.
+These set the maximum number of requests (default C<0>, meaning infinity)
+that are being processed by C<IO::AIO::poll_cb> in one call, respectively
+the maximum amount of time (default C<0>, meaning infinity) spent in
+C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
+of time C<poll_cb> is allowed to use).
+
+Setting C<max_poll_time> to a non-zero value creates an overhead of one
+syscall per request processed, which is not normally a problem unless your
+callbacks are really really fast or your OS is really really slow (I am
+not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
+
+Setting these is useful if you want to ensure some level of
+interactiveness when perl is not fast enough to process all requests in
+time.
 
-Useful if you want to ensure some level of interactiveness when perl is
-not fast enough to process all requests in time.
+For interactive programs, values such as C<0.01> to C<0.1> should be fine.
 
 Example: Install an Event watcher that automatically calls
-IO::AIO::poll_some with low priority, to ensure that other parts of the
+IO::AIO::poll_cb with low priority, to ensure that other parts of the
 program get the CPU sometimes even under high AIO load.
 
+   # try not to spend much more than 0.1s in poll_cb
+   IO::AIO::max_poll_time 0.1;
+
+   # use a low priority so other tasks have priority
    Event->io (fd => IO::AIO::poll_fileno,
               poll => 'r', nice => 1,
-              cb => sub { IO::AIO::poll_some 256 });
+              cb => &IO::AIO::poll_cb);
 
 =item IO::AIO::poll_wait
 
-Wait till the result filehandle becomes ready for reading (simply does a
-C<select> on the filehandle. This is useful if you want to synchronously wait
-for some requests to finish).
+If there are any outstanding requests and none of them in the result
+phase, wait till the result filehandle becomes ready for reading (simply
+does a C<select> on the filehandle. This is useful if you want to
+synchronously wait for some requests to finish).
 
 See C<nreqs> for an example.
 
-=item IO::AIO::nreqs
+=item IO::AIO::poll
 
-Returns the number of requests currently in the ready, execute or pending
-states (i.e. for which their callback has not been invoked yet).
+Waits until some requests have been handled.
 
-Example: wait till there are no outstanding requests anymore:
+Returns the number of requests processed, but is otherwise strictly
+equivalent to:
 
    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
 
@@ -911,14 +1212,11 @@
    IO::AIO::poll_wait, IO::AIO::poll_cb
       while IO::AIO::nreqs;
 
-=item IO::AIO::poll
-
-Waits until some requests have been handled.
+=back
 
-Strictly equivalent to:
+=head3 CONTROLLING THE NUMBER OF THREADS
 
-   IO::AIO::poll_wait, IO::AIO::poll_cb
-      if IO::AIO::nreqs;
+=over
 
 =item IO::AIO::min_parallel $nthreads
 
@@ -928,7 +1226,9 @@
 however, is unlimited).
 
 IO::AIO starts threads only on demand, when an AIO request is queued and
-no free thread exists.
+no free thread exists. Please note that queueing up a hundred requests can
+create demand for a hundred threads, even if it turns out that everything
+is in the cache and could have been processed faster by a single thread.
 
 It is recommended to keep the number of threads relatively low, as some
 Linux kernel versions will scale negatively with the number of threads
@@ -952,14 +1252,29 @@
 
 Under normal circumstances you don't need to call this function.
 
-=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs
+=item IO::AIO::max_idle $nthreads
+
+Limit the number of threads (default: 4) that are allowed to idle (i.e.,
+threads that did not get a request to process within 10 seconds). That
+means if a thread becomes idle while C<$nthreads> other threads are also
+idle, it will free its resources and exit.
+
+This is useful when you allow a large number of threads (e.g. 100 or 1000)
+to allow for extremely high load situations, but want to free resources
+under normal circumstances (1000 threads can easily consume 30MB of RAM).
+
+The default is probably ok in most situations, especially if thread
+creation is fast. If thread creation is very slow on your system you might
+want to use larger values.
+
+=item IO::AIO::max_outstanding $maxreqs
 
 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<aio_group> 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
+do queue up more than this number of requests, the next call to the
 C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
 function will block until the limit is no longer exceeded.
 
@@ -967,34 +1282,42 @@
 number of outstanding requests.
 
 You can still queue as many requests as you want. Therefore,
-C<max_oustsanding> is mainly useful in simple scripts (with low values) or
+C<max_outstanding> is mainly useful in simple scripts (with low values) or
 as a stop gap to shield against fatal memory overflow (with large values).
 
 =back
 
-=cut
+=head3 STATISTICAL INFORMATION
 
-# support function to convert a fd into a perl filehandle
-sub _fd2fh {
-   return undef if $_[0] < 0;
-
-   # try to generate nice filehandles
-   my $sym = "IO::AIO::fd#$_[0]";
-   local *$sym;
-
-   open *$sym, "+<&=$_[0]"      # usually works under any unix
-      or open *$sym, "<&=$_[0]" # cygwin needs this
-      or open *$sym, ">&=$_[0]" # or this
-      or return undef;
+=over
 
-   *$sym
-}
+=item IO::AIO::nreqs
+
+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).
+
+=back
+
+=cut
 
 min_parallel 8;
 
-END {
-   flush;
-};
+END { flush }
 
 1;
 
@@ -1024,7 +1347,7 @@
 scalars and other data passed into aio requests will also be locked and
 will consume memory till the request has entered the done state.
 
-This is now awfully much, so queuing lots of requests is not usually a
+This is not awfully much, so queuing lots of requests is not usually a
 problem.
 
 Per-thread usage:
@@ -1039,7 +1362,8 @@
 
 =head1 SEE ALSO
 
-L<Coro::AIO>.
+L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
+more natural syntax.
 
 =head1 AUTHOR