--- IO-AIO/README	2005/07/11 03:29:39	1.6
+++ IO-AIO/README	2006/02/01 23:43:17	1.15
@@ -15,6 +15,10 @@
         $_[0] > 0 or die "read error: $!";
      };
 
+     # AnyEvent
+     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->io (fd => IO::AIO::poll_fileno,
                 poll => 'r',
@@ -22,7 +26,7 @@
 
      # Glib/Gtk2
      add_watch Glib::IO IO::AIO::poll_fileno,
-               in => sub { IO::AIO::poll_cb, 1 };
+               in => sub { IO::AIO::poll_cb; 1 };
 
      # Tk
      Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
@@ -47,7 +51,9 @@
     using threads anyway.
 
     Although the module will work with in the presence of other threads, it
-    is currently not reentrant, so use appropriate locking yourself.
+    is currently not reentrant, so use appropriate locking yourself, always
+    call "poll_cb" from within the same thread, or never call "poll_cb" (or
+    other "aio_" functions) recursively.
 
 FUNCTIONS
   AIO FUNCTIONS
@@ -59,23 +65,36 @@
     error, unlike perl, which usually delivers "false") as it's sole
     argument when the given syscall has been executed asynchronously.
 
-    All functions that expect a filehandle will also accept a file
-    descriptor.
+    All functions expecting a filehandle keep a copy of the filehandle
+    internally until the request has finished.
 
-    The filenames you pass to these routines *must* be absolute. The reason
-    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.
+    The pathnames you pass to these routines *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 current
+    working directory.
+
+    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 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.
 
-    aio_open $pathname, $flags, $mode, $callback
+    aio_open $pathname, $flags, $mode, $callback->($fh)
         Asynchronously open or create a file and call the callback with a
         newly created filehandle for the file.
 
         The pathname passed to "aio_open" must be absolute. See API NOTES,
         above, for an explanation.
 
-        The $mode argument is a bitmask. See the "Fcntl" module for a list.
-        They are the same as used in "sysopen".
+        The $flags argument is a bitmask. See the "Fcntl" module for a list.
+        They are the same as used by "sysopen".
+
+        Likewise, $mode specifies the mode of the newly created file, if it
+        didn't exist and "O_CREAT" has been given, just like perl's
+        "sysopen", except that it is mandatory (i.e. use 0 if you don't
+        create new files, and 0666 or 0777 if you do).
 
         Example:
 
@@ -88,20 +107,27 @@
               }
            };
 
-    aio_close $fh, $callback
+    aio_close $fh, $callback->($status)
         Asynchronously close a file and call the callback with the result
         code. *WARNING:* although accepted, you should not pass in a perl
         filehandle here, as perl will likely close the file descriptor
-        itself when the filehandle is destroyed. Normally, you can safely
-        call perls "close" or just let filehandles go out of scope.
+        another time when the filehandle is destroyed. Normally, you can
+        safely call perls "close" or just let filehandles go out of scope.
+
+        This is supposed to be a bug in the API, so that might change. It's
+        therefore best to avoid this function.
 
-    aio_read $fh,$offset,$length, $data,$dataoffset,$callback
-    aio_write $fh,$offset,$length, $data,$dataoffset,$callback
+    aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
+    aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
         Reads or writes "length" bytes from the specified "fh" and "offset"
         into the scalar given by "data" and offset "dataoffset" and calls
         the callback without the actual number of bytes read (or -1 on
         error, just like the syscall).
 
+        The $data scalar *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).
+
         Example: Read 15 bytes at offset 7 into scalar $buffer, starting at
         offset 0 within the scalar:
 
@@ -110,24 +136,45 @@
               print "read $_[0] bytes: <$buffer>\n";
            };
 
-    aio_readahead $fh,$offset,$length, $callback
-        Asynchronously reads the specified byte range into the page cache,
-        using the "readahead" syscall. If that syscall doesn't exist (likely
-        if your OS isn't Linux) the status will be -1 and $! is set to
-        ENOSYS.
-
-        readahead() populates the page cache with data from a file so that
-        subsequent reads from that file will not block on disk I/O. The
+    aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
+        Tries to copy $length bytes from $in_fh to $out_fh. It starts
+        reading at byte offset $in_offset, and starts writing at the current
+        file offset of $out_fh. Because of that, it is not safe to issue
+        more than one "aio_sendfile" per $out_fh, as they will interfere
+        with each other.
+
+        This call tries to make use of a native "sendfile" syscall to
+        provide zero-copy operation. For this to work, $out_fh should refer
+        to a socket, and $in_fh should refer to mmap'able file.
+
+        If the native sendfile call fails or is not implemented, it will be
+        emulated, so you can call "aio_sendfile" on any type of filehandle
+        regardless of the limitations of the operating system.
+
+        Please note, however, that "aio_sendfile" can read more bytes from
+        $in_fh than are written, and there is no way to find out how many
+        bytes have been read from "aio_sendfile" alone, as "aio_sendfile"
+        only provides the number of bytes written to $out_fh. Only if the
+        result value equals $length one can assume that $length bytes have
+        been read.
+
+    aio_readahead $fh,$offset,$length, $callback->($retval)
+        "aio_readahead" populates the page cache with data from a file so
+        that subsequent reads from that file will not block on disk I/O. The
         $offset argument specifies the starting point from which data is to
         be read and $length specifies the number of bytes to be read. I/O is
         performed in whole pages, so that offset is effectively rounded down
         to a page boundary and bytes are read up to the next page boundary
-        greater than or equal to (off-set+length). aio_readahead() does not
+        greater than or equal to (off-set+length). "aio_readahead" does not
         read beyond the end of the file. The current file offset of the file
         is left unchanged.
 
-    aio_stat $fh_or_path, $callback
-    aio_lstat $fh, $callback
+        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.
+
+    aio_stat $fh_or_path, $callback->($status)
+    aio_lstat $fh, $callback->($status)
         Works like perl's "stat" or "lstat" in void context. The callback
         will be called after the stat and the results will be available
         using "stat _" or "-s _" etc...
@@ -147,24 +194,84 @@
               print "size is ", -s _, "\n";
            };
 
-    aio_unlink $pathname, $callback
+    aio_unlink $pathname, $callback->($status)
         Asynchronously unlink (delete) a file and call the callback with the
         result code.
 
-    aio_fsync $fh, $callback
+    aio_rmdir $pathname, $callback->($status)
+        Asynchronously rmdir (delete) a directory and call the callback with
+        the result code.
+
+    aio_readdir $pathname, $callback->($entries)
+        Unlike the POSIX call of the same name, "aio_readdir" reads an
+        entire directory (i.e. opendir + readdir + closedir). The entries
+        will not be sorted, and will NOT include the "." and ".." entries.
+
+        The callback a single argument which is either "undef" or an
+        array-ref with the filenames.
+
+    aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
+        Scans a directory (similar to "aio_readdir") and tries to separate
+        the entries of directory $path into two sets of names, ones you can
+        recurse into (directories), and ones you cannot recurse into
+        (everything else).
+
+        "aio_scandir" is a composite request that consists of many
+        aio-primitives. $maxreq specifies the maximum number of outstanding
+        aio requests that this function generates. If it is "<= 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.
+
+        Example:
+
+           aio_scandir $dir, 0, sub {
+              my ($dirs, $nondirs) = @_;
+              print "real directories: @$dirs\n";
+              print "everything else: @$nondirs\n";
+           };
+
+        Implementation notes.
+
+        The "aio_readdir" cannot be avoided, but "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 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 + "/." will be "stat"'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.
+
+    aio_fsync $fh, $callback->($status)
         Asynchronously call fsync on the given filehandle and call the
         callback with the fsync result code.
 
-    aio_fdatasync $fh, $callback
+    aio_fdatasync $fh, $callback->($status)
         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 "fsync" instead.
+
   SUPPORT FUNCTIONS
     $fileno = IO::AIO::poll_fileno
-        Return the *request result pipe filehandle*. This filehandle must be
-        polled for reading by some mechanism outside this module (e.g. Event
-        or select, see below). If the pipe becomes readable you have to call
-        "poll_cb" to check the results.
+        Return the *request result pipe file descriptor*. This filehandle
+        must be polled for reading by some mechanism outside this module
+        (e.g. Event or select, see below or the SYNOPSIS). If the pipe
+        becomes readable you have to call "poll_cb" to check the results.
 
         See "poll_cb" for an example.
 
@@ -173,7 +280,8 @@
         this regularly. Returns the number of events processed. Returns
         immediately when no events are outstanding.
 
-        You can use Event to multiplex, e.g.:
+        Example: Install an Event watcher that automatically calls
+        IO::AIO::poll_cb with high priority:
 
            Event->io (fd => IO::AIO::poll_fileno,
                       poll => 'r', async => 1,
@@ -181,13 +289,14 @@
 
     IO::AIO::poll_wait
         Wait till the result filehandle becomes ready for reading (simply
-        does a select on the filehandle. This is useful if you want to
+        does a "select" on the filehandle. This is useful if you want to
         synchronously wait for some requests to finish).
 
         See "nreqs" for an example.
 
     IO::AIO::nreqs
-        Returns the number of requests currently outstanding.
+        Returns the number of requests currently outstanding (i.e. for which
+        their callback has not been invoked yet).
 
         Example: wait till there are no outstanding requests anymore:
 
@@ -211,23 +320,30 @@
               if IO::AIO::nreqs;
 
     IO::AIO::min_parallel $nthreads
-        Set the minimum number of AIO threads to $nthreads. The default is
-        1, which means a single asynchronous operation can be done at one
-        time (the number of outstanding operations, however, is unlimited).
+        Set the minimum number of AIO threads to $nthreads. The current
+        default is 4, which means four asynchronous operations can be done
+        at one time (the number of outstanding operations, 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.
 
-        Under normal circumstances you don't need to call this function, as
-        this module automatically starts some threads (the exact number
-        might change, and is currently 4).
+        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.
 
     IO::AIO::max_parallel $nthreads
         Sets the maximum number of AIO threads to $nthreads. If more than
-        the specified number of threads are currently running, kill them.
-        This function blocks until the limit is reached.
+        the specified number of threads are currently running, this function
+        kills them. This function blocks until the limit is reached.
+
+        While $nthreads are zero, aio requests get queued but not executed
+        until the number of threads has been increased again.
 
         This module automatically runs "max_parallel 0" at program end, to
         ensure that all threads are killed and that there are no outstanding
@@ -241,11 +357,20 @@
         block until some requests have been handled.
 
         The default is very large, so normally there is no practical limit.
-        If you queue up many requests in a loop it it often improves speed
-        if you set this to a relatively low number, such as 100.
+        If you queue up many requests in a loop it often improves speed if
+        you set this to a relatively low number, such as 100.
 
         Under normal circumstances you don't need to call this function.
 
+  FORK BEHAVIOUR
+    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 parent process has been reached again.
+
 SEE ALSO
     Coro, Linux::AIO.