On Mon, 11 Aug 1997 23:07:46 -0700  Jonathan Stone wrote:

> Just a heads-up:
> 
> After some great help from Michael Hitch debugging and walking through
> the code, I've fixed the `fastest known' IP checksum code, committed
> it, and changed the kernel config to use it.  If TCP starts breaking
> in -current pmax kernels tomorrow, that's probably why.
> 
> There's more tuning I plan to do on this code soon.

For the blissfully ignorant, what real world performance difference is
this going to make?  Will TCP stack be "much faster"?

Simon.