Re: [Bloat] Bufferbloat at LUG talk - Meeting Report

[Oliver Hohlfeld <oliver@net.t-labs.tu-berlin.de>]

On 12/19/2012 01:20 PM, Jonathan Morton wrote:
> I think we're talking about the "many tabs open" problem.
> 
> But this bothers me as well, actually. Lots of tabs shouldn't affect the
> network unless some of the pages in them are actively transferring data
> for some reason. I've seen lots of pages that have heavy animation or
> Javascript in them, but unless Facebook is even nastier than I was
> previously aware of, that doesn't really translate to high network traffic.

That was exactly the point I tried to stress in the post quoted by Neil;
An open tab does not automatically translate to network traffic, i.e.,
there is not necessarily causality between "open tab" and "Skype
problem". The pure existence of open tabs doesn't say anything; they
must trigger data transfers, there is no network impact otherwise. If
at all and how web transfers impair voice flows depends on a whole lot
of other aspects.

I often observe Javascript rendering in Firefox to fully load one CPU
core, which sometimes interferes with Skype calls on my systems. But
that's not a networking problem and not related to bufferbloat.

Oliver