In message <1396.923406158@hrriss.hprc.tandem.com>Stefan Grefen writes
>In message <199904061248.WAA02276@avalon.reed.wattle.id.au>  Darren Reed wrote
>:
>> In some email I received from Stefan Grefen, sie wrote:
>> [...]
>> > Also I think we do very enthusiastic acking (I know it is recommended 
>> > by the working group,  ..) 
>> > 
>> > Most of the options shouldn't matter ... but it may influence our 
>> > statemachine a little to do less acks ...
>> 
>> how about sysctl's to control how many delayed acks are kept ?
>> 
>
>:-)) Want to start a fight with the guys attending the working groups ?? :-))
>
>If IRC there was a decent flamewar^H^H^HXXXX discussion at the point when
>this change went into NetBSD.

Gosh, the last big dust-up I remember was about advertised MSSes...
My first thought, without a whole lot of analysis, is that we shouldn't 
be sending all of those dup ACKs, but that the other side certainly
shouldn't be barfing quite so badly on them.  What OS is m3 running!?
How up to date is the NetBSD system?

[Yah, if I was a *real* TCP guru, I could tell from the trace... :-)]

Kevin
kml@nas.nasa.gov