So 2010 is nearly done and I must say that 2010 in storage went pretty much as I expected. 3Par, Isilon and Compellent being gobbled up by bigger companies; no special surprises there. New hardware from HDS, NetApp and IBM; no special surprises there either. And more Cloud-washing from everyone; from Public-Cloud to Private-Cloud, everyone wants a piece of the action. I've taken to calling my test-environment at home a Pico-Cloud.
So what will 2011 bring us? These are some of my guesses and thoughts.
Even More Cloud?
I expect EMC to continue painting just about everything they do with Cloud-wash and adding a layer of virtual tarnish to the Cloud. Despite all of this, I think EMC are going to be interesting as always.
It's no secret that we should expect some kind of NetApp killer in the coming together of Clariion and Celerra; with the much maligned Celerra-brand to die and it all to come together under some Unified Storage brand. We should also be expecting very tight integration with VMware; I think EMC still feel very hurt that NetApp have managed to do a better integration job with VMware, whether perception or reality. EMC are going to focus some serious attention on NetApp and believe that technically they can now compete; expect the war of words to escalate.
However, having built a NetApp-like Unified Storage platform; EMC have muddied the water again by buying Isilon and yet again have a standalone NAS product. An internal battle brewing within EMC? If they've learnt the lessons from the DG and Clariion; one would hope not but history does have a habit of repeating itself. At the very least, expect some serious marketing spin to try to differentiate the capabilities. Don't believe it for one minute; if the future of most storage is predominantly file with a ever diminishing proportion of block; Isilon become extremely important very quickly to EMC with the new Unified Storage Platform getting squeezed between Isilon and Symmetrix. Granted not a 2011 problem, more a 2013 issue but something worth thinking about when planning investments.
A side question on Isilon, how quickly do EMC try to move Isilon from its BSD roots to their more preferred internal Linux platform? Now, that's a holy-war brewing!
Huge Portfolio?
HP have far too many storage lines and this has left many of their user-base confused and more importantly, I suspect many of their user-base are feeling reluctant to invest more heavily in an HP strategy.
David Scott is going to have to be ruthless over the next six months and he will have to move fast to get his charges all pointing in the same direction and singing from the same hymn-book. The future of EVA will need to be clarified very quickly; letting the market decide seems to be pretty rash at this point and is adding to the confusion. I'm expecting a statement of direction from them by the middle of the year allowing customers to put together an investment strategy.
HP's problem is how they scale 3PAR's technology both up and down; I'd expect announcements from them on this. Or are they going to have to look at Lefthand for this.
HP's other problem is that they still don't have a really strong file story; they have stories but most of these have as much substance as a Dan Brown thriller. Could HP acquire again; if there were anyone left to buy, that would not surprise me but I don't see anyone who could fill this hole for them.
Net Apprehension
NetApp refreshed their hardware and released another version of Ontap 8; also announced a virtual appliance version of the filer and by all accounts, they've had a stonking 2010 sales-wise. They continue to out-grow their competitors and continue to gather plaudits; so what will 2011 bring?
Well NetApp aren't a company without problems as much as they like to claim and they appear to have got away with a lot; customers are still giving them a fair amount of slack but…
OnTap 8 needs to get tightened up and there needs to be a single mode; this is certainly NetApp's plan and there is some deserved embarrassment when you bring up the current situation. So expect this to be rectified at sometime in 2011 with OnTap 8 cluster-mode to be fully functionally equivalent to 7-mode with the advantage that it is cluster-able. EMC's acquisition of Isilon makes this all the more important and NetApp cannot afford this to be delayed much longer.
NetApp's teams are tired; I would say that the company is struggling to keep up with it's own growth. I've heard this from people inside and out; teams are stretched too thin and the company is going to have to grow the number of foot soldiers. NetApp are not the only company with this problem but they've always run very lean with no fat; admirable in start-up but NetApp can probably afford to grow some girth.
And finally, NetApp need to acquire someone relatively substantial and not only for the obvious reason but also to prove that they can do so successfully. I don't expect NetApp to stray too far from the storage beat with someone like CommVault in their sights but that will probably bring them into a bidding war with Dell.
Ring the Dell?
It appears that Dell want to be the storage game; getting involved in and loosing a very public auction for 3Par and then ending up the year by purchasing Compellent. If you had asked me at the beginning of 2011; I would have bet very heavily on 3Par going to HP and probably not so heavily on Compellent ending up with Dell but it seems a more logical fit than vice versa.
Dell have three interesting pieces of a storage jigsaw right now; Equalogic and Compellent, solid SME products and Exanet, a clustered NAS product. The latter needs some serious investment to turn it into more than an intellectual curiosity; it's market presence is somewhat less than zero and ever since Dell acquired it, it has been invisible.
Somehow Dell have to turn all of this into a coherent strategy but Dell have a secret weapon; a couple of years ago, Dell bought a small British storage consultancy called The Networked Storage Company. They have continued to run this as an independent entity; TNWSC generally get involved with enterprise customers when they are looking to issue RFPs etc and you can hear the sighs of pain/irritation/annoyance when a vendor finds out that they are responding to a TNSWC tinged RFP. They also run birds of the feather type get-togethers for storage end-users and the agendas always look interesting even if for various reasons I've not managed to get to one yet. I like to think of them as a more sober #storagebeers.
Dell by now should have a real insight into the problems that enterprise customers are trying to solve; turning this into a product is going to be more challenging but at least they've been listening.
Its Bazza Magic?
IBM's announcement of the v7000 based on SVC technology was one of the more stand-out storage announcements; not because of the technology, most of the industry had been expecting something like this for some time but because it wasn't strangled by the other interests in IBM. Even long-standing rivals were quietly pleased to see that IBM finally came to their senses and realise that the answer to many of their storage problems had been sitting in Hursley for sometime.
The DS8000 also appears to the array that refuses to die; in a year dominated by zombie-tinged media, the DS8K is almost the zombie array; every-time someone thinks it's dead, up it rises. Unfortunately, like zombies; it will never be popular and people will keep trying to smash it with shovels and whatever else comes to hand.
Next year tho'; XIV should get its long awaited upgrades, time will tell whether these will be enough to see it become a strategic stand-alone product. Infiniband connectivity between the nodes should finally be with us; this was discussed at the IBM launch many moons ago; a 'flash cache' type enhancement to help XIV cope with more random workloads and give the SATA a boost; clustering to improve scalability and I am wondering if we could see 2.5" drives make an appearance to improve floor-space-to-byte density?
I am also expecting to see significant enhancements to v7000; with both some of the artificial limiters coming off but also Storwize making an appearance with block level compression. Obviously, feature enhancements will make an appearance in SVC as well.
Also expect Storwize to make an appearance in the SONAS product range; expect IBM to launch a smaller version of SONAS to compete with their partner NetApp but also aimed at the smaller Isilon deployments. Finally, expect IBM's storage OEM agreements to become less important to them.
Highly Dependable Storage?
Finally, HDS have refreshed their USP platform with the VSP; feature-rich, enterprise-ready and very capable but is it really where the real growth is? I think this is HDS' real problem; how do they show real relevance to the problems that many storage managers are facing?
I don't believe that they will but I'm expecting them to push very hard on the Hitachi Unified Compute Platform as a catalyst for IT transformation. I think HDS have a very rich seam to mine here in their traditional high-end market place especially with those customers who are very uncomfortable with putting all of their eggs into Cisco's basket
And just perhaps they will finally buy BlueArc? Perhaps we can convince Dell or HP to put in a bid, just to get things moving?
And Storagebod?
Well, 2010 was the year when somebody finally allowed me to have storage in my job title again; which was nice as my nascent storage team went from having a few hundred terabytes under management from something closer to three petabytes with an ever steepening growth curve.
Next year brings the challenges of render-farms, 3D HD editting stations, migrating most of our storage into a new building, building disaster recovery capabilities, multiple upgrades and lots more fun I hope.
Happy New Year!!
Martin
