Storagebod Rotating Header Image


Virtually Pragmatic?

So why have EMC joined the storage virtualisation party and although they are calling it federation, it is what IBM, HDS and NetApp amongst others call storage virtualisation? So why do this at this time after warning about dire consequences about doing so in the past.

There are probably a number of reasons to do this; there have certainly been commercial pressures to do so, I know of a number of RFPs which have gone out from large corporates which have mandated this capability; money talks and in an increasingly competitive market, EMC probably have to tick this feature box.

The speed of change in the spinning rust market appears to be slowing, certainly the incessant increase in the size of hard disks is slowing and there means that there might be less pressure to technically refresh the spindles and a decoupling of the disk from the controller makes sense. EMC can protect their regular upgrade revenues at the controller level and forgo some of the spinning rust revenues. They can more than make up for this out of maintenance revenues on the software.

But I wonder if there is a more pressing technological reason and trend that means that it is a good time to do this; that is the rapid progress of flash into the data-centre and how EMC can work to increase the acceleration of adoption. It is conceivable that EMC could be looking shipping all-flash arrays which allow a customer to continue to enjoy their existing array infrastructure and realise the investment that they have made. It is also conceivable that EMC could use a VMAX like appliance to integrate their flash-in-server more simply with a third party infrastructure.

I know nothing for sure but the size of this about turn from EMC should not be understated; Barry Burke has railed against this approach to storage virtualisation for such a long time, there must be some solid reasoning to justify it in his mind.

Pragmatism or futurism, a bit of both I suspect.