Re: MAE-EAST Moving? from Tysons corner to reston VA.
On 16 Jun 2000 michael.dillon@gtsip.net wrote:
On Fri, 16 June 2000, "Richard A. Steenbergen" wrote:
In a public exchange point where you're talking to multiple networks across a shared media it makes sense to do GigE, multiple GigE, 10GigE, etc,
What is the largest MTU that you can use across a GigE fabric?
I think this would be extremely foolhardy. The common number that all those using jumbo frames should support is 9000 bytes (not 9k aka 9216). This would probably need to be a condition of using GigE at the NAP, in order to achieve any kind of common support, and you're eliminating some vendor gige support (assuming their network can even carry the 9k packets TO the nap without requiring even more work and possible problems). Has anyone tested these maximium sized jumbo frames with 802.1q vlan tagging to see exactly how much (or how little) inter-vendor support really exists? -- Richard A Steenbergen <ras@e-gerbil.net> http://www.e-gerbil.net/humble PGP Key ID: 0x138EA177 (67 29 D7 BC E8 18 3E DA B2 46 B3 D8 14 36 FE B6)
Just to clarify, when folks talk about 9k MTUs, they gnerally mean 8940 bytes. That is, twice the MTU for FDDI and DS3. It seems to me that if the MTU is going to be increased at some point that working in multiples is the right way to go about it. On Fri, Jun 16, 2000 at 10:46:13PM -0400, Richard A. Steenbergen wrote:
I think this would be extremely foolhardy. The common number that all those using jumbo frames should support is 9000 bytes (not 9k aka 9216).
---------------------------------------------------------------------- Wayne Bouchard [Immagine Your ] web@typo.org [Company Name Here] Network Engineer http://www.typo.org/~web/resume.html ----------------------------------------------------------------------
On Fri, 16 Jun 2000, Wayne Bouchard wrote:
Just to clarify, when folks talk about 9k MTUs, they gnerally mean 8940 bytes. That is, twice the MTU for FDDI and DS3. It seems to me that if the MTU is going to be increased at some point that working in multiples is the right way to go about it.
8940 9000 9216 10420, sigh what I wouldn't give for a copy of by Rich Seifert's Gigabit Ethernet book in front of me right now. Will someone find some IEEE material that discusses some of this and try to find what is closest to the real number we should be aiming for. I'm "thinking" its 9000... Anything from 802.3ae 10GigE? -- Richard A Steenbergen <ras@e-gerbil.net> http://www.e-gerbil.net/humble PGP Key ID: 0x138EA177 (67 29 D7 BC E8 18 3E DA B2 46 B3 D8 14 36 FE B6)
participants (2)
-
Richard A. Steenbergen -
Wayne Bouchard