[142505] in North American Network Operators' Group
Re: [pfSense Support] Strange TCP connection behavior 2.0 RC2 (+3)
daemon@ATHENA.MIT.EDU (Mikael Abrahamsson)
Wed Jun 29 01:23:18 2011
Date: Wed, 29 Jun 2011 07:22:24 +0200 (CEST)
From: Mikael Abrahamsson <swmike@swm.pp.se>
To: Cameron Byrne <cb.list6@gmail.com>
In-Reply-To: <BANLkTin4RBcVAZaz9kwoBouHmT1TBndkbQ_xc9E=OFFx4GEr5w@mail.gmail.com>
Cc: "williamejsalt@googlemail.com" <williamejsalt@googlemail.com>,
NANOG list <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
On Tue, 28 Jun 2011, Cameron Byrne wrote:
> My point was that if end-hosts had Hybla or something similar, these
> proxies can be removed providing a better end-to-end solution.
Well, then you run into the nice problem of the RNCs only having 400
kilobytes of buffers per session and will drop packets if they receive
more packets than that, or sometimes even just because they receive a
burst of a few tens of packets at GigE linerate (because the customer with
large TCP window size is talking to a GigE connected server).
The recommended "solution" from the vendor was to tune the client to a
smaller TCP window size so that their RNC wouldn't get such a large burst.
*sigh*
--
Mikael Abrahamsson email: swmike@swm.pp.se
