[190739] in North American Network Operators' Group
BGP & MTU
daemon@ATHENA.MIT.EDU (Jared Mauch)
Sat Jul 23 15:47:02 2016
X-Original-To: nanog@nanog.org
From: Jared Mauch <jared@puck.nether.net>
In-Reply-To: <520e997e-9c83-3d1c-b99b-b818e3ea3b16@Janoszka.pl>
Date: Sat, 23 Jul 2016 15:46:55 -0400
To: Grzegorz Janoszka <Grzegorz@Janoszka.pl>
Cc: nanog@nanog.org
Errors-To: nanog-bounces@nanog.org
> On Jul 22, 2016, at 1:37 PM, Grzegorz Janoszka <Grzegorz@Janoszka.pl> =
wrote:
>=20
> On 2016-07-22 15:57, William Herrin wrote:
>> On a link containing only routers, you can safely increase the MTU to
>> any mutually agreed value with these caveats:
>=20
> What I noticed a few years ago was that BGP convergence time was =
faster with higher MTU.
> Full BGP table load took twice less time on MTU 9192 than on 1500.
> Of course BGP has to be allowed to use higher MTU.
>=20
> Anyone else observed something similar?
This has been well known for years:
=
http://morse.colorado.edu/~epperson/courses/routing-protocols/handouts/bgp=
_scalability_IETF.ppt
You have to adjust the MTU, Input queues and such. The default TCP =
stack is very conservative.
- Jared=
