On Wed, 2005-09-14 at 11:19, Hal Rosenstock wrote: > On Wed, 2005-09-14 at 11:08, Eitan Zahavi wrote: > > I attach also some Analyzer file that show paylen is wrong, > > I will look at this shortly. Unfortunately I do not have IBA 1.2 decode > so this is by hand.
It doesn't look right. You either don't have all the changes or haven't restarted things since you picked them up. The first thing I notice in the trace is that middle segments don't have their payload length set to 0. So I'm not sure this was a valid experiment. -- Hal _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
