RE: Jumbo Frames in 10GbE?

[gwinn@ed.ray.com (Joe Gwinn)]

At 3:01 PM 99/6/21, Rubin, Larry wrote:
>Actually, it is not a "system issue", but a standards issue. Because a
>vote was taken and had greater than 75% agreement, it will take another
>vote (assuming the chair rules it in order) to pass with greater than
>75% to put jumbo packets into our objectives. This does not mean that
>they are kept out of the eventual standard, BTW. It only means that they
>are not one of our objectives. There's plenty of precedent for that.

I would claim that it is a systems issue, because standards do not exist
for their own sake.

If a sufficient number of people feel that this or any other issue should
be addressed, it will be, procedural details aside.


>Should that standard be the 10GbE? The voting members of the current
>study group obviously do not think so. If you believe very stongly that
>they should be, then I think the procedure is to request the chair (Mr.
>Thatcher) to let you give a presentation to the study group (although
>that might be ruled out of order since the group already voted it down).

Actually, I didn't have a strong feeling either way, but do feel that the
issue was inevitable and thus should be considered as part of the debate on
what BER goal 10GbE should adopt, 10^-12, or something better, such as
10^-13.  If the packets are larger, one can argue the BER should be
smaller, to preserve the packet error rate.  This also ties into the
discussion about how big a packet a CRC can protect.

I hasten to add that most links with a nominal 10^-12 BER in practice seem
to achieve 10^14 or 10^-15, or else don't work at all, so it isn't obvious
to me that changing the BER goal will in fact change delivered system
performance.   For one thing, I wonder if the observed 10^14 or 10^-15
error performance is limited by optical issues, or by electrical issues
such as self-interference within the transmitter and receiver electronics.


However, the wide disparity in reactions to the proposal suggest to me that
true consensus may not yet have been achieved, despite the one plenary
vote, so this may be a necessary debate.


Joe Gwinn