Purdue faculty, campus units getting state-of-the-art storage system for research data
June 20, 2014
The people who brought Purdue researchers the best suite of supercomputers dedicated to use by faculty on a single campus in the country are beginning a similar program to meet Purdue’s faculty and campus unit research data storage needs.
The Research Data Depot, as the new service from ITaP Research Computing (RCAC) is called, will be a state-of-the-art data system designed, configured and operated for the needs of Purdue researchers.
While ITaP has always offered research data storage for computational and archival purposes in connection with the Community Cluster Program supercomputers, the Research Data Depot will make available over 2 petabytes of storage to any Purdue research group or campus unit in need of a high-capacity central solution for storing large, active research data sets at a competitive price.
“We made a decision to invest in this state-of-the-art research data storage system for two reasons,” says Gerry McCartney, system chief information officer, vice president for information technology and Olga Oesterle England Professor of Information Technology. “First, this ‘big data’ era, in research no less than other endeavors, makes a resource like the Research Data Depot essential to Purdue’s research enterprise. Second, we have heard from faculty a growing chorus of requests for a central place to store research data securely and reliably, access and move it rapidly in the course of doing their research and share it easily with colleagues and collaborators.”
At a cost of approximately $150 per terabyte annually, a research group can purchase or expand storage space in the Research Data Depot as the need arises. Data will move over an upgraded high-speed campus research network, whether to the community clusters, office and lab computers for computation and analysis, or from high-performance instruments that generate large data streams.
In addition, the Research Data Depot will incorporate technology for sharing access to and moving data among research collaborators not only around campus but around the country, or the globe, as well. The system will be safe but configurable by faculty for use on a project or research group basis and in on-campus and off-campus collaborations.
All data will be protected from accidental deletion and mirrored at two sites on different ends of campus to ensure rapid access, reliability and recoverability to an extent not possible with research data storage resources currently maintained by individuals, labs or other campus units — be those departmental servers, stacks of hard drives on a lab bench, or a USB drive in somebody’s pocket.
Since 2008, hundreds of faculty members and their students have come to rely on Purdue’s Community Cluster Program to meet computational needs in their research. The highly reliable, cost effective partnership between ITaP and faculty researchers has garnered national and international attention in higher education and high-performance computing circles and also has built the nation’s most powerful campus supercomputer for Purdue researchers two years running.
Plans are to have the Research Data Depot online during the fall semester, says Preston Smith, ITaP Research Computing (RCAC) manager of research support. As with the community clusters, researchers and campus units will be able to purchase capacity in the Research Data Depot easily through the “Purchase” link atop the ITaP Research Computing (RCAC) website, www.rcac.purdue.edu.
Also like the clusters, Smith notes, the Research Data Depot will have an easy-to-use Web interface for configuring space, setting access permissions to it, sharing, and more.
For more information, contact Preston Smith, firstname.lastname@example.org or 49-49729.