Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

RE: Jumbo Frames in 10GbE?

I agree that if there is enough support for jumbo-frames then the proper thing to do would be to request a call for interest. The implementation of jumbo-frames will affect all ethernet equipment, not just 10GbE and thus should be done in a separate study group just as the 802.3ac and others have started. As an end user, I have several hundred pieces of ethernet equipment that will have compatibility problems if this becomes standard. It has been suggested that the compatibility problem could be addressed by auto-negotiating the frame size. I have had problems with devices that do not auto-negotiate to the correct duplex mode. I think this would simply add another level of complexity that may not be worth the effort. It concerns me that the debate over implementing jumbo-frames in the 10 GbE standard will only serve to slow the standards process. Adding 2 more cents to the ante.

Mike




At 03:01 PM 6/21/99 -0500, 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.

Is the market going to jumbo packets? Obviously. Many (most?) of us already handle them.

Should jumbo packets be standardized? It is my opinion that they should be.

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).

Another way to go about it would be to request a call of interest of the 802.3 group at the next plenary for a separate standard. This was what the VLAN (802.3ac) group did.

Just my $0.02,
Larry Rubin

-----Original Message-----
From: gwinn@xxxxxxxxxx [SMTP:gwinn@xxxxxxxxxx]
Sent: Monday, June 21, 1999 2:39 PM
To: Booth, Brad
Cc: HSSG_reflector (E-mail)
Subject: Jumbo Frames in 10GbE?


At 4:24 PM 99/6/17, Booth, Brad wrote:
>Just a small point. One of the objectives that passed with greater than
>75% in Coeur d'Alene was to "preserve minimum and maximum FrameSize of
>current 802.3 Std."

I don't know that the issue is going to stay decided all that long, based
on the recent article "Jumbo Frames gather support" (Jeff Caruso, Network
World, 14 June 1999, page 6), which states that IETF has published a
working document proposing that ethernet frames be made larger than the
current 1,500-byte maximum, the basic rationale being to reduce the packet
rate and thus load on packet-handling components of the system. In short,
this is a system issue, and cannot really be decided solely at the MAC
level.

If jumbo frames are to come, 10GbE would be a logical place to start.

The issue will ultimately be decided by an IEEE Ballot Group, not a
Plenary. If the market is really going to bigger packets, as this article
implies, it will be hard to resist.

Joe Gwinn



The above is in response to the following:

> >Issues 3 - Bit Error Rate
> >The assumption will be that this is 10-12. If someone wishes to
>challenge
> >this they should bring a presentation to the next meeting providing
> detailed reasoning why this needs to change.
>
> It strikes me that the issue of larger maximum packet sizes will likely
> come up, just as it did for GbE. If 10GbE goes to 9 KB packets,
>the design
> center BER would need to go to 10^-13 to maintain the same theoretical
> packet loss rate. I'm not sure how much effect this would have in
> practice, as most gigabit links achieve much better than 10^-12,
>if they
> work at all. Anyway, these items are ripe for debate and decision.

**** end of message ****


<<<<