EMC Storage Data Deduplication Technology Goes Enterprise

Having shelled out $2.1 billion last year to win its bidding war with NetApp to acquire Data Domain to solidify its hold on the small but growing data deduplication market, EMC is looking to raise the bar with two new solutions.

The storage giant has doubled the capacity of its data dedupe workhorse, the Data Domain DD880, with support for up to 7.1 petabytes of logical backup storage, as well as thrown in data encryption capabilities. EMC has also introduced the Data Domain Global Deduplication Array (GDA), its first multi-controller offering with up to 14.2 PB of logical backup capacity and throughput up to 12.8 TB/hour.

EMC’s Shane Jackson, senior director of product marketing in the backup recovery systems division, tells Channel Insider that the new offerings open up the high-end enterprise market to the channel as well as making it easier to sell lower-end solutions into companies that would previously have excluded EMC because they didn’t want multiple dedupe vendors. He says one of the sales barriers for its 5,000 global partners had been the perception that because EMC only offered single controller solutions, it didn’t scale.

Capacity was never an issue, and the company has seen fantastic growth in the last two years, he says. From 2004 to 2010, throughput increased 90x and capacity 225x, adds Jackson, so it was more perception than reality. GDA removes that potential barrier from discussion.

With the beefed up DD880 due out this quarter, users can consolidate up to 180 concurrent backup jobs or extend the retention period when used as a replication target for up to 180 remote offices. Data Domain Encryption integrates with the Data Domain high-speed, inline deduplication process and provides administrator selectable 128-bit or 256-bit Advanced Encryption Standard (AES) algorithms for encrypting all data before it is written to disk.

The company has also enhanced its Data Domain Replicator software with significant new features, including a one-to-many directory replication topology and breakthrough low bandwidth optimization for limited WANs and small sites, increasing bandwidth efficiencies by up to a hundred percent.  

The GDA, which will also ship this quarter, presents a single inline deduplication storage pool to the backup application across two DD880 controllers, distributing parts of the deduplication process to the backup servers to reduce network load and increase the throughput performance of the GDA controllers. It offers more than 3x faster backup throughput per controller than competitive deduplication configurations and is anchored by the native speed advantages of the multi-core CPUs in the GDA controllers and the Data Domain SISL (Stream-Informed Segment Layout) scaling architecture that minimizes the number of disk accesses required in the deduplication process.  At initial release, the platform supports Symantec NetBackup and Backup Exec through backup server-based OpenStorage plug-in software.  Later in 2010, it will also support EMC NetWorker using integrated software.  

With the EMC Data Domain Replicator software option, the GDA can automate WAN vaulting for use in disaster recovery (DR), remote office backup, or multi-site tape consolidation. A single GDA can support a replication fan-in of up to 270 remote offices using smaller deduplication storage systems such as the DD140 or the DD600 series appliances. Additionally, for fast offsite protection and consolidation of tape out operations, the GDA provides up to 54 TB/hour of replication throughput.

EMC has been prepping the channel for the new offerings, but those efforts will be accelerated with the official launch, says Jackson, including an hour-long Webcast detailing the opportunities. He says deduping has been selling well as organizations struggled to do more with less and he expects this market surge to continue because of the strong ROI.

"The value proposition of deduplication is very strong. More and more customers are starting to see that and expand their use cases."