[fc417fc802]

So order multiple drives, transfer the data to them, and drop them in the mail to the client. That should always be the higher bandwidth option, but in a sane world it would also be less cost effective given the differences in amount of energy and sorts of infrastructure involved.

The reason to switch away from fiber should be sustained aggregate throughput, not transfer cost.

[ryao]

The other guy was also comparing them based on transfer cost. Given that 1TB can be divided across billions of locations, shipping physical drives is not a feasible alternative to transit at Amazon in general.

[fc417fc802]

I'm not trying to claim that it's generally equivalent or a viable alternative or whatever to fiber. That would be a ridiculous claim to make.

The original example cited people writing custom scripts to download all your stuff blowing your budget. A reasonable equivalent to that is shipping the interested party a storage device.

More generally, despite the two things being different their comparison can nonetheless be informative. In this case we can consider the up front cost of the supporting infrastructure in addition to the energy required to use that infrastructure in a given instance. The result appears to illustrate just how absurd the current pricing model is. Bandwidth limits notwithstanding, there is no way that the OPEX of the postal service should be lower than the OPEX of a fiber network. It just doesn't make sense.

[ryao]

That is true. I was imagining the AWS egress costs at my own work where things are going to so many places with latency requirements that the idea of sending hard drives is simply not feasible, even with infinite money and pretending the hard drives had the messages prewritten on them from the factory. Delivery would never be fast enough. Infinite money is not feasible either, but it shows just how this is not feasible in general in more than just the cost dimension.