[178644] in North American Network Operators' Group
Re: Bufferbloat related censorship at Virgin Media
daemon@ATHENA.MIT.EDU (Dave Taht)
Sun Mar 1 19:14:37 2015
X-Original-To: nanog@nanog.org
In-Reply-To: <54F3A906.7080806@paradoxnetworks.net>
Date: Sun, 1 Mar 2015 16:14:33 -0800
From: Dave Taht <dave.taht@gmail.com>
To: Jack Bates <jbates@paradoxnetworks.net>
Cc: NANOG <nanog@nanog.org>
Errors-To: nanog-bounces@nanog.org
On Sun, Mar 1, 2015 at 4:04 PM, Jack Bates <jbates@paradoxnetworks.net> wro=
te:
> On 3/1/2015 5:28 PM, Dave Taht wrote:
>>
>>
>> My IP address is apparently now banned from accessing your site at
>> all, for "advertising", on this thread:
>>
>>
>> http://community.virginmedia.com/t5/Up-to-152Mb/Bufferbloat-High-Latency=
-amp-packet-loss-when-connection/td-p/2773495
>>
>>
>
> I don't see how codel is related to the customer complaint from their
> perspective. The problem appears to be high latency on downstream with
> little to no upstream. I'd probably call it off-topic advertising. The on=
ly
> thing that seems to relate to codel is the user's use of bufferbloat in t=
he
> topic. Nothing the user can do will fix the downstream to my knowledge. N=
ot
> that I'm extremely knowledgeable on the subject.
It is 100% possible to fix excessive downstream buffering from some
misconfigured device with a shaper on the download *on the CPE or
home router*.
I have been doing that for 15 years. So has everyone that uses nearly
any of the shapers that are available for Linux, at least.
http://burntchrome.blogspot.com/2014_05_01_archive.html
doing it yourself, right, requires a good measurement, and you lose
just a little bit of single-flow bandwidth - typically 5% - but you
get it all back with faster tcp ramp up times, huge improvements in
dns lookups, voip, gaming, and other traffic.
it generally works way better than policers do.
>
> Jack
--=20
Dave T=C3=A4ht
Let's make wifi fast, less jittery and reliable again!
https://plus.google.com/u/0/107942175615993706558/posts/TVX3o84jjmb
