EMC Breaks Out Distributed Deduplication Package

 
 
By Chris Preimesberger  |  Posted 2010-05-11
 
 
 

EMC execs must love the month of May, when the company can host and feed scores of partners and customers, do some razzle-dazzling of potential buyers, and share news of new products and services at its EMC World conference.

Usually, the event is staged in a resort-like place like Orlando, Fla. This year, the world's largest independent storage maker, based in Hopkinton, Mass., elected to stay close to home in Boston. Nothing wrong with that, but anybody wishing to soak up some near-tropical sunshine will simply have to wait until another day.

EMC continues to draw on 2009's $2.2 billion Data Domain acquisition for new purposes.

In April, EMC launched a Data Domain global deduplication array that is capable of backing up 12.8TB of data per hour (a rate of 3.5G bps), has a top usable capacity of 280TB and can handle up to 270 concurrent write streams.

On May 11, EMC revealed something called DD Boost (for Data Domain Boost), data protection software that the company claims is the first such package to "optimize and accelerate" disk-based backup integrated with deduplication storage.

Data deduplication eliminates redundant data from a disk storage device in order to lower storage space requirements, which in turn lowers data center power and cooling costs and lessens the amount of carbon dioxide produced in generating power to run the hardware.

DD Boost's secret sauce is that it distributes the deduplication process, identifying data segments in-line as they arrive in a Data Domain storage system. It analyzes the segments to determine which blocks are new, then compresses and forwards only the unique segments to the storage array.

This pre-editing of data blocks speeds throughput in the overall backup load and can reduce local network traffic by a large margin-possibly as high as 80 to 95 percent-because redundant data segments do not enter the array in the first place.

A side benefit of the DD Boost process is that it reduces workload strain on the overall backup process, EMC said.

DD Boost will work with non-EMC backup products, such as Symantec NetBackup and Backup Exec, and is available now, EMC said.

Ironically, the same product for EMC's own NetWorker backup package won't be ready for prime time until the second half of 2010. Go here for more information.

Rocket Fuel