>> I've also seen troubles which appear to be difficulty with
>> back-to-back packets, though they have been less well understood.
> The problems with back-to-back packets are pretty well understood,

Well, I really meant, "the problems I saw I did not investigate enough
to be confident they really were back-to-back problems, nor, if so,
what the relevant aspect of back-to-back packets was responsible".

> Or are you talking about sending back-to-back packets without the
> mandatory quiet periods between packets?

Well, as I say, I don't really know.  It was really just "some kind of
back-to-back trouble is my front-runner theory for this problem", but,
as with so many problems, I never truly got to the bottom of it.

Given the problem I saw receiving min-size packets, it wouldn't
surprise me if there were ancient Ethernet interfaces that demanded
more quiet time between packets than the spec does.

/~\ The ASCII				der Mouse
\ / Ribbon Campaign
 X  Against HTML	       mouse@rodents.montreal.qc.ca
/ \ Email!	     7D C8 61 52 5D E7 2D 39  4E F1 31 3E E8 B3 27 4B