Lawrence Berkeley National Laboratory Meets Exponential Data Storage Increases to Support Scientific Research
 
 

Lawrence Berkeley National Laboratory Meets Exponential Data Storage Increases to Support Scientific Research

Printer View Printer View

Lawrence Berkeley National Laboratory, a U.S. Department of Energy National Laboratory operated by the University of California, aims to address urgent scientific challenges by advancing sustainable energy, protecting human health, creating new materials, and revealing the origin and fate of the universe. Founded in 1931, Berkeley Lab’s scientific expertise has been recognized with 12 Nobel prizes.

Managed by Berkeley Lab, the National Energy Research Scientific Computing Center (NERSC) is the primary scientific computing facility for the Office of Science in the U.S. Department of Energy (DOE). Funded by DOE’s Office of Advanced Scientific Computing Research, NERSC is one of the largest facilities in the world devoted to providing computational resources and expertise for basic scientific research. More than 4,000 scientists use NERSC to perform basic scientific research across a wide range of disciplines, including climate modeling, research into new materials, simulations of the early universe, analysis of data from high energy physics experiments, investigations of protein structure, and a host of other scientific endeavors.


 
Challenges and Solutions

A word from Lawrence Berkeley National Laboratory

  • “At NERSC, our challenge is to figure out how to grow our data storage capacity exponentially without growing our budget exponentially. Oracle’s StorageTek T10000C tape drives deliver that combination, which is why we signed on as early adopters.” – Jason Hick, Storage Systems Group Leader, National Energy Research Scientific Computing Center, Lawrence Berkeley National Laboratory

To provide the high-performance computing its users require and to maintain its reputation as one of the best-run scientific computing facilities in the world, NERSC must ensure its IT systems are available, reliable, and secure. At the same time, NERSC’s data archiving needs grow exponentially—by 50% to 70%—each year, and, because it is a federally funded laboratory, it faces increased pressure to contain and reduce costs, and more efficiently use space and power.

NERSC, a longtime early adopter of new tape drive technology with nearly 150 Oracle tape drives already in place, including Oracle’s StorageTek T10000B tape drive, to store more than 20 petabytes of data, selected Oracle’s StorageTek T10000C tape drive. The StorageTek T10000C provides five times the capacity of previous models and 25% more storage capacity than any other competing solution. It, therefore, enables NERSC to meet its growing data storage needs with up to five times fewer StorageTek SL8500 modular library systems, keeping overall costs down.  

StorageTek T10000C’s higher capacity makes the business case easy for Jason Hick, storage systems group leader at NERSC. “When it comes to adding capacity, we either spend money on old media or invest in new media for the StorageTek T10000C tape drives, which will position us to reduce our operational budget going forward,” he said.

NERSC is deploying 18 StorageTek T10000C tape drives and swapping out old drives when possible. The new tape drive technology enables NERSC to free up to 80% of the tape cartridge slots in its existing libraries, enabling it to avoid adding more libraries, which would be costly. The StorageTek T10000C tape drives also provide the lowest available uncorrected bit error rate of 1x10-19, which is vital because NERSC keeps only one backup copy of data. StorageTek T10000C also includes partitioning features that NERSC hopes to take advantage of in the future to reduce data retrieval times.

In addition to long-term storage, NERSC also requires fast access to its data to meet scientists’ needs. The tape drive technology not only enables users to write archives files, it also enables them to retrieve and read files when necessary, which makes up about 30% of NERSC’s tape drive activity. Finally, tape drive technology is long lasting, uses power efficiently, and requires minimal cooling, helping NERSC meet DOE’s requirements for energy efficiency.

 
 

 
 

Oracle Product and Services

Why Oracle

Berkeley Lab’s NERSC selected Oracle’s StorageTek T10000C tape drives because Oracle provides the highest tape storage capacity on the market. StorageTek provides  up to five terabytes of uncompressed data, which is more than 25% above what other tape drives can provide.

Implementation Process

NERSC worked with Dynamic Systems to purchase the tape drives and is in the process of deploying them.

Partner

  • Oracle Partner
    Dynamic Systems

  

Resources