Subject: Re: Socket buffer accounting and TCP
To: Charles M. Hannum <mycroft@MIT.EDU>
From: Stefan Grefen <firstname.lastname@example.org>
Date: 09/03/1998 09:55:24
In message <199809022232.SAA26150@opus.mit.edu> "Charles M. Hannum" wrote:
> >> Perhaps the threshold should be based on the number of mbufs in the
> >> chain.. i.e., compress if you have more than 3-4 mbufs in the socket
> >> buffer.
> >Or compress when there's room in the mbuf - this won't happen if
> >you're receiving big packets.
> I considered that for about 30 seconds ... and then realized it
> assumes a correlation between mbuf size and MSS/MTU, which is not
> necessarily correct, especially in the presence of different transport
> layers and different networking protocols.
I think should've invested anoher 10 seconds (thats what I needed ....)
If the mbufs have no room (or not much) than we're wasting headers
and can start compressing to reclaim the header space if the amount of
wasted headerspace is a certain percentage of buffered data.
If there is a mbuf with lots of space (eg. the new one fits in) then we can
Stefan Grefen Tandem Computers Europe Inc.
email@example.com High Performance Research Center
--- Hacking's just another word for nothing left to kludge. ---