|Thread Links||Date Links|
|Thread Prev||Thread Next||Thread Index||Date Prev||Date Next||Date Index|
Good catch! That's what I get for typing late on a Monday night. J I should have stated "Given that Jumbo Frames capability has been implemented by some companies, ..."
The point was that there are companies out there that have implemented Jumbo Frame capability, and a consortium may be a better way to proceed to develop a compatibility standard rather than generating an IEEE standard. This is how the RMII consortium was done. There were a few companies that realized they were developing a lower pin count MII, and upon showing each other their wares, they discovered that they had similar concepts. A consortium was formed to develop an RMII standard, which permitted the work to be done quicker and with less overhead than if they had developed an IEEE standard.
If there is a real interest in Jumbo Frames, then it should be developed on its own and not burden other standards' development.
Level One Communications, Austin Design Center
(512) 407-2135 office
(512) 589-4438 cellular
From: Bruce_Tolley@xxxxxxxx [SMTP:Bruce_Tolley@xxxxxxxx]
Sent: Tuesday, June 22, 1999 10:29 AM
To: Booth, Brad
Cc: 'HSSG_reflector (E-mail)'
Subject: RE: Jumbo Frames in 10GbE?
You wrote: "Given that Jumbo Frames are already being used in the market by a
In terms of market acceptance of jumbo frames I think we need to stick to the
facts. By market acceptance I mean real end user customers using the feature in
real operational networks.
2 or 3 companies are shipping NICs that support jumbo frames. One switch vendor
is shipping a switch that supports jumbo frames. For jumbo frames to work, my
understanding is that you need both the switch port and the NIC to be jumbo
enabled. This switch vendor does not have a large market presence according to
published third party market research reports. I can only conclude that only a
small number of customers to date have hardware that could support jumbo frames.
the consortium (#1 solution) would probably be the fastest
way to generate a standard. If there is a real need to have it as an
IEEE standard, then creating its own standard (#2 solution) would be the
best way to go. The development would be similar to 802.3ac and could
probably be done in about the same time span. Trying to roll it in to
the 10GbE is going to be the hardest to do, because there is already an
objective that the FrameSize will remain the same and there seems to be
a general feeling that this could impact the 10GbE development.