[67241] in North American Network Operators' Group
Re: MTUs - Was: Strange public traceroutes return private RFC1918 addresses
daemon@ATHENA.MIT.EDU (Iljitsch van Beijnum)
Fri Feb 6 08:44:25 2004
In-Reply-To: <OFAC9BF5A4.FF61C6AE-ON80256E32.0038FBF3-80256E32.003925C5@radianz.com>
Cc: nanog@merit.edu
From: Iljitsch van Beijnum <iljitsch@muada.com>
Date: Fri, 6 Feb 2004 14:43:50 +0100
To: Michael.Dillon@radianz.com
Errors-To: owner-nanog-outgoing@merit.edu
On 6-feb-04, at 11:24, Michael.Dillon@radianz.com wrote:
>> So there we are. Want to bet on whether 40 GigE will still have the
>> 1522
>> byte limit?
> Given the growing number of folks who will only buy xGigE equipment
> that supports 9000 byte MTUs
I had that happen one time: when evaluating some gigE switches a few
years ago I complained that they would only do 1500 bytes. A week later
they had new boards that did 64k for me. :-)
> I'd say the chances are very good that 40GigE will no longer have a
> 1522 byte limit.
I don't think vendors are going to risk building 40GE stuff that can
only do 1500, but the IEEE on the other hand would look pretty stupid
by giving in at 40G after sticking to 1500 at 1 and 10.
