Vice President of Editorial
Published: 11 Dec 2012
Rich Castagna offers a list of five developments that we all want to see in the data storage market in 2013 but, alas, probably won't. Why? Because vendors continue to drag their heels.
Hope springs eternal, especially at the outset of a new year. Even for a jaded, somewhat cynical, ex-New Yorker like me, the image of 12 fresh months is rejuvenating. Having survived 2012, hard-pressed storage managers can now breathe a sigh of relief and focus on the bounty that 2013 will bring.
Well … maybe. Last year was probably the busiest I've ever seen in the storage market, with the release of lots of new products, super-fast flash having an impact practically everywhere, and storage companies pursuing mergers and acquisitions like bargain-crazed shoppers at Walmart. But despite all the new developments on the tech front and the stretching of the data center into the cloud, a lot of other fundamental storage stuff had few changes.
In the spirit of the new year, here's my list of five developments that we all want to see in the data storage market in 2013 but, alas, probably won't. But it won't be because these are tough tech nuts to crack; it'll be because vendors continue to drag their heels for a variety of reasons.
- Real cloud storage standards. SNIA has its Cloud Data Management Interface (CDMI) standard, which on the surface looks like a good step toward standardizing cloud storage metadata to make it easier to move data among cloud services. But few vendors have signed on, and the effort is looking more like window dressing from a clutch of vendors protecting the turf they've already staked out. Other than SNIA and maybe the open-source OpenStack project, there's not much else going on with cloud storage standards. But this certainly isn't a surprise for most storage pros; storage companies protect their bottom lines by aggressively maintaining proprietary formats and protocols that make switching to competing products difficult and often too costly to consider. So why should cloud storage be any different?
- Let's cut big data down to size. I mean that both literally and figuratively. There's a pretty good chance we wouldn't be subject to all this big data propaganda if instead of Hadooping us into thinking we need big data this and big data that, vendors delivered products that helped us sift through our data to find the meaningful stuff without requiring Herculean efforts and a whole new set of products. At one time, data classification looked like an emerging market with companies such as Kazeon Systems, NextPage, Scentric and StoredIQ, among others. A few have since disappeared, others were scarfed up by bigger companies and some are still plugging away. Data classification could make short shrift of data analysis, but that would put the brakes on the big data juggernaut and make all those big data products look … er, less than necessary.
- Widely available primary storage dedupe/compression. "Widely available" is the key part of this New Year's wish. The technology has been around for years (even decades), so that's not the problem. Vendors say it isn't so easy to add data reduction to arrays; it takes processing power and the results will never be as dramatic as with backup dedupe. We know all that, but we also know that NetApp's been doing it for years. Dell and IBM bought Ocarina and Storwize, respectively, and they've hardly been heard from since. Dare we hope that they and other storage vendors will finally step it up in 2013 and deliver something storage managers sorely need?
- Serious and honest cost/benefit analysis of virtualization. When we talk to vendors about storage for virtual servers or virtual desktops, we seem to always hear how the stuff you have on your data center floor now just isn't up to the task of supporting virtualized environments. So virtualization means new storage systems -- preferably liberally laced with NAND flash -- and replacing all those bargain-basement servers and desktops with $50,000 gazillion-core colossal servers. But what happens when the network strains under that load? There are plenty of good reasons to virtualize -- easier management, disaster recovery and so on -- but it's far from the blanket solution that vendors claim even if they stick "cloud" onto their product names.
- Practical alternatives to RAID. RAID is approximately 25 years old and beginning to show its age as disk capacities climb to levels that make it impractical for data protection. You could just mirror everything, of course; it's about the easiest RAID implementation around and it's effective even if it's the least economical way to RAID drives. A handful of companies are trying to shake us from our RAID mindset and get us to think about alternatives like erasure codes and other variations that disperse data across a number of nodes and can withstand failures with greater resilience than RAID. The technology is there, we're just waiting for some of the major storage vendors to give it a boost.
One final thing I'd like to see in 2013: the New York Jets winning the Super Bowl. I'm not sure which is less likely to happen -- any of the above five coming to fruition in 2013 or the Jets hoisting the Lombardi trophy one more time. As John Lennon sang, "You may say I'm a dreamer …"
About the author:
Rich Castagna is editorial director of TechTarget’s Storage Media Group.