It's not true to say that A&A don't oversubscribe. Instead the situation is that they're happy to buy more capacity to fulfil their offer, within reason.

If A&A subscribers could in theory move 10Tbps (if they all simultaneously did some sort of download from a hypothetical unlimited source) but in reality they never do and it peaks at something like 100Gbps, A&A are fulfilling their promise by ensuring they've got 100Gbps to do that.

Typically you'll never notice the difference, except on your bill, because if they had 100x more bandwidth upstream they'd pay a lot of money for that, even though it was unused and they'd have to pass that to you in the medium term.

However, the reality is a little closer to oversubscribing. Suppose A&A are paying for 10Gbps on a particular port somewhere, and at their busiest time of the week it typically runs at 9.8Gbps. Unfortunately the company selling it only wants to offer 100Gbps as the next step up, for five times the money. Another 10Gbps port isn't an option as there are no 10Gbps ports free. So A&A decides to sit on the problem, nobody is suffering at 9.8Gbps.

Next week it hits 10Gbps and seems likely it'd have gone to 11Gbps if that was possible. Oops. The firm they're buying that capacity from still has 100Gbps available, but they agree at last that they could add more 10Gbps ports, and will do so for the same price as the existing port. Unfortunately it means buying a new Cisco router, which Cisc says is on back order, it'll arrive in July.

Are A&A going to throw five times the money at the problem for this burst of maybe 30-40 minutes per week? Or are they going to tell you sorry but it'll be July and until then bandwidth at that peak across that particular link isn't what it ought to be? They're going to do the latter. Because at the end of the day it's a business. RevK is a good guy, but he's not looking to bankrupt the company to make some point.