Robin at StorageMojo has an interesting article up (right after the one about Violin maybe being dead).
I won’t comment on that second one, other than to say I disagree with his analysis and conclusions. As the day job is nominally a competitor (we’ve seen them in a deal, once) I am biased. But the fundamental analysis simply doesn’t look good for them (or Fusion, or …). They need a larger player to buy them. I don’t know if Toshiba or Sandisk would … that would entail competing with their customers. But most of the pure flash array plays have a limited lifetime without tight coupling the computing within it.
The article I wanted to comment on was the first. And he had written this:
Scale-out converged computes and storage that starts in the $20s.
We (the day job) agree with the analysis. Red Hat is going to continue pushing OpenShift + others, and have people do the “DIY” clouds and storage. As many people discover when they do this, the box label where it says “just add hardware for an instant cloud” is about as far from reality as one could be.
Which is why the second and third points are so important. They could be easily lumped together as “scale out tightly coupled computing and storage appliances with low entry cost, easy scale up and out.”
Which, we wholeheartedly agree with. As we’ve been doing this tightly coupled thing for the life of the company, building scale out computing and storage appliances, and formally productizing them almost a decade ago.
We’ve been building these appliances to attack a number of different problems we see as being important to customers. And we are seeing very strong growth in demand.
We’ve been arguing for years that the tight coupling between computing, storage and network pipes is what matters most for scale out, and our benchmarks demonstrate this again and again.
Not having venture backers limits what we can do and how quickly we can grow … this is one of the harder realities of life. But its nice to hear that others believe strongly in the model … from potential competitors to industry pundits. Its was hard being a lone voice in the wilderness evangelizing a world view. Its rewarding to now see this world view adopted and repeated by so many.
I agree with Robin’s two latter points as noted. There aren’t that many tightly coupled computing and storage companies out there. But the products they are building are changing the game whereever they are used.