The New Buying Dynamics for Storage, Servers and Converged Infrastructure

For 50 years we’ve bought stuff based on what the “box” could do – how much capacity, how fast, how expensive. We made our decision, picked our vendor, and we lived with it.

When we ran out of something, we bought another box. And another. We loved our first box, and hated our 87th. Such has been the life of the infrastructure buyer.

Today we don’t (or shouldn’t) buy like that any longer. Those metrics don’t matter anymore.

What matters is this:

Those are very different criteria from “my box is better than your box”. No one wants to pay for everything to be the fastest, because only 8% of the time does our stuff (data, processing, etc.) actually need to be fast.

Thus, in storage, 10% of our capacity should be flash (or memory, or whatever is the fastest we can afford), and the rest should probably be in the cloud – constantly becoming cheaper, always accessible, and always available.

If you are a converged system – the same thing holds true. The cloud is the great enabler of this paradigm. The cloud lets you put stuff away cheap, access it from anywhere, and keep it up (if you do it right).

Orchestration Becomes Critical

Thus, the most important criteria moving forward is the orchestration of the entire system. Making sure whatever needs to be fast is on the stuff that is fastest, and managing everything else back to the cheapest is the name of the game.

I said this with showgirls at EMC World in Vegas years ago. I’m still right. And I still love showgirls.

Ironically, converged systems are not converged at all, presuming they have a cloud element integrated. They are deconstructed systems managed holistically. Crazy.

The big money won’t be in the kit, it will be in the intelligence. Data-aware, baby. Put the stuff that needs to be at point A at time B there, and move the other stuff out of the way. That’s the hard part.