Debunking the Bandwidth Hog Myth

Benoit Felten has a very well reasoned post on his personal blog, fiberevolution (which I found via Nate Anderson at Ars).

Felten makes two ringing points, the first around how hogs are identified. Namely that their reasoning doesn’t seem to be based on how aggressive downloaders actually affect the experience of other network users, but rather pointing the finger at those users whose bandwidth simply tops the list of utilization.

For those service providers with data caps, these are usually set around 50 Gbyte and go up to 150 Gbyte a month. This is therefore a good indication of the level of bandwidth at which you start being considered a “hog”. But wait: 50 Gbyte a month is… 150 kbps average (0,15 Mbps), 150 Gbyte a month is 450 kbps on average. If you have a 10 Mbps link, that’s only 1,5 % or 4,5 % of its maximum advertised speed!

The second point questions even the technical possibility of unfair consumption of available bandwidth.

As Herman explains in his post, TCP/IP is by definition an egalitarian protocol. Implemented well, it should result in an equal distribution of available bandwidth in the operator’s network between end-users; so the concept of a bandwidth hog is by definition an impossibility. An end-user can download all his access line will sustain when the network is comparatively empty, but as soon as it fills up from other users’ traffic, his own download (or upload) rate will diminish until it’s no bigger than what anyone else gets.

He doesn’t leave his arguments hanging, though, but challenges ISPs to furnish standardized data to either back their claim that a minority of users are responsible for the majority of network woes or put to rest what he suggests is merely a bit of rhetoric they are advancing to try to re-capture the opportunity for price discrimination.

ISPs are not alone in trying to twist rhetoric to camouflage their motives, to better their bottom line. Given the vast array of public goods that the internet enables and supports, I think our tolerance for specious argument should be lower than in typical market interactions. Bravo, Benoit, for demanding ISPs lay their cards on the table so we can move on to more substantive debates.

One Reply to “Debunking the Bandwidth Hog Myth”

Leave a Reply

Your email address will not be published. Required fields are marked *