Michael Lotz 63d5a418ab Cleaned up and optimized Message2.cpp. It avoids as many unnecessary copies as it can now.
The unflatten time is now reduced to about a third of the current BMessage implementation but it's still
about half as quick as R5 (we're talking about microseconds here).
A third version of BMessage that operates purely on a flat buffer is in the works. We'll see which one
will be faster for normal uses.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13821 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-07-25 00:06:34 +00:00
..