High Performance Computing | News
Penn State Research Center Shifts to Solid State Storage
- By Dian Schaffhauser
A research computing center at Penn State University seeking to reduce backup time has upgraded its traditional hard disk storage to solid state drives with technology from Texas Memory Systems. Research Computing and Cyberinfrastructure, a unit of the university's IT Services organization, runs high performance computing systems and does software development and programming support for research, teaching, and other institutional purposes.
Each night the unit would hope that its use of 200 separate 15K RPM hard drives would be sufficient to handle backup operations and minimize the impact on production operations. Backups would take as long as six hours to complete; during backups other system operations would slow down.
In an effort to improve the backup process, the IT team for the research unit settled on the idea of using solid state drives (SSD) to handle the workload. After evaluating SSD products from four vendors, the team chose a pair of RamSan-810 storage systems from Texas Memory. These were placed in a high-availability mirrored configuration designed to exploit a replication functionality of the unit's IBM General Parallel File System storage.
The new implementation improved the nightly backup times by six--reducing a six-hour effort to a single hour. At the same time, the university said, the new setup improved input/output operations and minimized related power, cooling, and floor space costs.
"With some of the other solutions we tested, we poked and pried at them for weeks to get the performance where the vendors claimed it should be," said Michael Fenn, a Penn State systems administrator. "With the RamSan, we literally just turned it on and that's all the performance tuning we did... It seemed very stable and it just worked out of the box."
Dian Schaffhauser is a senior contributing editor for 1105 Media's education publications THE Journal and Campus Technology. She can be reached at firstname.lastname@example.org or on Twitter @schaffhauser.