At 18:43 -0400 6/17/98, [email protected] wrote:
>With careful link layer and router configuration
>good performance was possible. Without such
>careful configuration, no matter how much TCP
>parameters were tweaked, TCP performance
>would be miserable. The local link considerations
>far outweighed the effect of end-to-end
>TCP parameter tweaking.
Good point, and one we (I think) inserted into the "Standards Mechanisms"
draft. All the work being done on TCP and TCP-based applications (the
"tweaking") assumes that the link layer protocol has already been optimized
to utilize the channel. This is in somes ways an easier problem, since -
as you point out - the layer 2 protocol terminates (or can terminate) at
the ends of the satellite link.
What makes TCP issues so thorny is the end-to-end assumption inherent in
layer 4 protocols. The satellite link is ideally supposed to be unaware of
TCP; in the real world we get into the PEP issues.
Hans Kruse, Associate Professor and Director
McClure School of Communication Systems Management, Ohio University
9 S. College Street
Athens, OH 45701
614-593-4891 voice, 614-593-4889 fax, [email protected]
This archive was generated by hypermail 2b29 : Mon Feb 14 2000 - 16:14:44 EST