Not over, we need systems that are both fast and scalable. But I suspect than in five years since now most people will consider a much more reasonable thing to shard client side, by hand, and in the most uncool ways a system that can deliver 100k requests/second than an automatically sharding system with 10k requests/second. My guess is that currently the queries/watt figure is not taken seriously enough.

With Redis we will shortly start working full time at "Redis cluster" so it's not that we don't care :) Just I think the first goal should be to have a very efficient "single" node, and then going the step forward trying to retain the same speed if possible.