Posted by: Michael Morisy
IBM, Storage in 2010, Storewize
A short blurb in the Israeli daily Haaretz has the storage world talking: IBM is negotiating to acquire data storage startup Storewize for $140 million. Rather than offering storage solutions directly, Storewize focuses on boosting existing network-attached storage by compressing and decompressing data before it’s stored or accessed with a drop-in appliance, similar to how more widely-deployed WAN optimization technology works. Storewize claims it can reduce storage utilization by 50% to 90%, reducing an organization’s data center footprints, cooling costs and necessary hardware all in one fell swoop.
With public customers like Polycom reducing storage needs upwards of 60% on everything from disaster recovery backups to Oracle databases, it’s no surprise IBM took notice, offering Storewize’s STN-6000p series through its business partner program.
Organizations could certainly use any opportunity to cut down on storage demands: While costs per gigabyte continue to drop, facilities costs for data centers remain high and the amount of data that needs to be stored has increased six-fold in the past four years with no signs of slowing.
Are we seeing the beginnings of a storage compression war, just as we saw a storage deduplication war start three years ago? Quite possibly: The Register reports that Storewize competitor Exar will likely get a boost as other storage vendors look to beef up their own optimization offerings. If war is imminent, vendors and users alike might take Arun Taneja’s advice from last time around, when he warned that while the need was very real, results and benefits from the current technology need to be fully vetted:
So, be prepared to see a barrage of data coming your way. I am suggesting to the vendor community that they run their products using a common dataset to identify the differences in approaches. I think you should insist on it. Without that, the onus is on you to convert their internal benchmarks to how it might perform in your environment. You may even need to try the system using your own data
What do you think? Are storage compression appliances going to be standard issue in your upcoming storage deployments, and can you trust the public case studies to apply to your situation? Let me know in the comments or e-mail me directly.