S.Korea broadband firm sues Netflix after traffic surge

Mark Tinka mark at tinka.africa
Mon Oct 11 07:58:14 UTC 2021

On 10/10/21 23:57, Sabri Berisha wrote:

> I have worked for ISPs. And I remember the late 90s. Bandwidth was $35/mbit
> on average, at least for the outfit where I was. Consumers paid roughly $40
> for their DSL connections, which at the time went up to 2Mbit depending
> on the age of the copper and distance to the DSLAM. Consumer connections
> were oversubscribed, on average, 1:35 to 1:50. B2B connections got a better
> deal, 1:10 to 1:15.
> It was simply not feasible to offer 1:1 bandwidth and still make a profit,
> unless you're charging fees the average consumer cannot afford.
> Especially considering that the average user doesn't even need or use that
> much bandwidth. It's a recurring discussion. People demand more bandwidth
> without considering whether or not they need it. End-users, business subs,
> and host-owners at large enterprises where I worked. The last ones are the
> funniest: entire racks using no more than 100mbit/s and hostowners are
> demanding an upgrade from 10G to 25G bEcaUse LaTenCy.
> The last consumer ISP I worked at had a very small subset of users that
> really needed bandwidth: the "download dudes" who were 24/7 leeching news
> servers, and the inevitable gamers that complained about the latency due
> to the links being full as a result of said leechers. In that case, a
> carefully implemented shaping of tcp/119 did the trick.

It's the conundrum of a shared resource. Like managing 1 lift (elevator, 
for the Americans :-)) that needs to move a building full of people 
between floors.

In the early days of the Internet, circuits were long, expensive and 
slow. Equipment cost a lot for what you could get out of it, and content 
was mostly centralized, making getting to it even more expensive, and 
hence, entrenching the current model.

However, in an era where content is making a push to get as close to the 
eyeballs as possible, kit getting cheaper and faster because of merchant 
silicon, and abundance of aggregated capacity at exchange points, can we 
leverage the shorter, faster links to change the model?


More information about the NANOG mailing list