NetApp De-dupes Genome Data

NetApp De-dupes Genome Data

By Greg McNevin

October 10, 2008: While genome scientists continue to do groundbreaking work, the process of creating and analysing genomic information requires a substantial amount of data storage capacity. To head this exponential growth off at the pass, NetApp has announced that it will be helping the US’s Duke Institute to reign in storage requirements with its de-duplication technology.

The Duke Institute for Genome Sciences and Policy (IGSP) saw its data storage infrastructure that grew from 4TB to 300TB within two years, with much of the data contained in large Oracle databases on dedicated servers and locally attached storage.

“We just bought more disks and kept giving them to Oracle,” says database administrator Rob Wagner. “Over time this proved to be very difficult to manage. Server sprawl and inefficient data storage utilisation became a constant headache.”

To resolve this rapid growth dilemma, IGSP embarked on a server virtualisation project, collapsing 40 physical servers down to just 3 for the institute's Oracle applications. In conjunction with this project, IGSP also made the transition from locally attached storage to consolidated, network-attached NetApp FAS systems.

NetApp says that this server consolidation and data de-duplication has helped reduce storage requirements for genomic information by 83 percent, while simultaneously decreasing the institute's overall hardware, power, and administration requirements.

It has also helped streamline management, with IGSP system administrator Alan Cowles noting that previously he spent more time managing 60TB to 70TB of direct-attached storage than he now does managing the 225TB of NetApp storage IGSP has now.

“NetApp has saved us a lot on storage for VMware,” says Cowles. “When we originally set up VMware, I allocated about 2.4TB for it. With NetApp de-duplication, I've been able to shorten that down to less than 700GB. We now see an average of 83 percent reduction in redundant data on our VMware systems.”

Comment on this story

Business Solution: