Velocity 2011: Artur Bergman, "Artur on SSD's"

Look. :) Yeah, the build machine churns a lot. But that work should be primarily done by the FS cache, by buffers. Yes, it's going to write out those small files, but if DragonflyBSD has any kind of respectable kernel, though should be a solid curve, not lots of bursts. I would love if my old colleague Przemek from Wikia would talk about the SSD wear on our MySQL servers which had about 100k-200k databases per shard. We wore the _fuck_ out of some SSDs. You should replace your HDDs with SSDs, though, for a number of reasons, and take the long view, as kryptistk noted the OP is doing. Really compare the cost of SAS 15k drives and Intel 320s or 530s. But I think in his place, you can take the words of the inimitable Mr. Bergman: [this video] Stop wasting your life. But don't expect a machine that does lots of random IO, like a database, to have 1-2% SSD wear after two years. It might not last two years. If it does, use it more. Aren't you making money with these drives? ;)

I find it a bit disturbing how this post reaches the top of HN. But I suppose I shouldn't be surprised. I probably live in my own little bubble, but only lately have I realized that NoSQL has two audiences: (1) People for whom normalization can't work because of their application's characteristics and the limitations of current hardware. (2) People who just don't understand basic relational concepts, or why they were invented in the first place. It's kinda sad. I've consulted on projects where people implemented sharding before adding any indices to MySQL. The thing about being in group (1) is that you can also recognize when the ground shifts beneath your feet. Artur Bergman is one of those guys. [this video]