Re: ATM over Satellite Experiment

Rick Jones (raj@cup.hp.com)
Thu, 26 Aug 1999 11:04:11 -0700

Perhaps there is some correlation to the MTU being used and how many
segments can be sent into the window, interacting with SWS stuff. That
the LAME stuff was smoother could be the use of a smaller MTU - 1500
bytes right?

Of course, the "right" way to do this is to take packet traces :) It
might also help explain the jaggies for the larger than CIP MTUs -
perhaps the chance that a given segment is corrupted is increased -
seeing rtx's in the trace would show that - it could also be infered
from netstat statistics on the sender and receiver. (retrans and
checksum failures).

rick jones

-- 
these opinions are mine, all mine; HP might not want them anyway... :)
feel free to email, or post, but please do not do both...
my email address is raj in the cup.hp.com domain...