BitTorrent swarms have a deadly bite on broadband nets

Tue Oct 23 06:28:14 UTC 2007

On Tue, 23 Oct 2007 00:35:21 EDT, Sean Donelan said:
> This doesn't explain why many universities, most with active, symmetric
> ethernet switches in residential dorms, have been deploying packet shaping 
> technology for even longer than the cable companies.  If the answer was
> as simple as upgrading everyone to 100Mbps symmetric ethernet, or even
> 1Gbps symmetric ethernet, then the university resnet's would be in great 
> shape.

If I didn't know better, I'd say Sean was trolling me, but I'll bite anyhow. ;)

Actually, upgrading everybody to 100BaseT makes the problem worse, because
then if everybody cranks it up at once, the problem moves from "need upstream
links that are $PRICY" into the "need upstream links that are $NOEXIST".

We have some 9,000+ students resident on campus.  Essentially every single
one has a 100BaseT jack, and we're working on getting to Gig-E across the
board over the next few years.

That leaves us two choices on the upstream side - statistical mux effects (and
emulating said effects via traffic shaping), or find a way to trunk 225 40GigE
links together.  And that's just 9,000 customers - if we were a provider
the size of most cable companies, we'd *really* be in trouble.

Fortunately, statistical mux effects and a little bit of port-agnostic traffic
shaping (you go over a well-publicized upload byte limit for a 24 hour span,
you get magically turned into a 56k dialup), we fit quite nicely into a
single gig-E link and a 622mbit link.

Now if any of you guys have a lead on an affordable way to get 225 40GigE's
from here to someplace that can *take* 225 40Gig-E's... ;)

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 226 bytes
Desc: not available
URL: <http://mailman.nanog.org/pipermail/nanog/attachments/20071023/f6bdf27d/attachment.sig>