Datadobi

Oak Ridge National Laboratory With Active Archive Solutions

Including redundant array of independent tapes, 120 drives, 60,000 tapes, for 107PB
This is a Press Release edited by StorageNewsletter.com on 2017.02.13

AddThis Social Bookmark Button

The Active Archive Alliance announced that Oak Ridge National Laboratory (ORNL) has upgraded its active archive solutions to enhance the integrity and accessibility of its vast amount of data to meet its increasing data demands and enable fast file recall for its users.

 

Titan Oak Rdge

ORNL is home to the US' most powerful supercomputer for open science, Titan. It is capable of 27 petaflops and can handle quadrillions of calculations simultaneously for scientific simulations. More than 1,200 users have access to the supercomputer and its file storage systems, where simulation data is stored so that users can access data-sets as needed.

"These active archive upgrades were crucial to ensuring our users' data is both accessible and fault-tolerant so they can continue performing high-priority research at our facilities," said Jack Wells, director of science, National Center for Computational Sciences, ORNL. "Our storage-intensive users have been very pleased with our new storage capabilities."

The active archive solutions include Redundant Array of Independent Tapes (RAIT) technology as well as enterprise tape drives and a 18PB disk cache. The center has more than 120 tape drives and the ability to house 60,000 tapes. The archive has 107PB of tape storage capacity of which 59PB is being used at present, and it has the ability to scale to a data capacity of 498PB.

"We are looking at best-of-breed solutions all the time, whether those be for the disk cache or tape layer or for the application managing those hierarchical storage systems," said Quinn Mitchell, HPC storage system administrator, the Oak Ridge Leadership Computing Facility (OLCF). "We are always evaluating our current storage system to find the best active archive solutions to meet both our center's needs and the needs of the next generation of computational scientists."

Case study

Articles_bottom