Panasas, Inc., today announced that Los Alamos National Laboratory (LANL) is using the Panasas ActiveScale Storage Cluster™ to enable its Pink supercomputer to operate without local disks in the compute cluster. By eliminating local disks, LANL has achieved significant improvements in reliability and availability, increasing the mean time between failure (MTBF) for Pink's compute nodes from once a week for a comparable system to once every seven weeks. LANL's use of the Panasas Storage Cluster enables improved scalability and reduced overall management costs of the Pink supercomputer, ultimately increasing the productivity of Pink's user community.
LANL is one of the world's leading supercomputer facilities and part of the National Nuclear Security Administration (NNSA). The Pink supercomputer is a 9.8 teraflop Linux Cluster that provides about one million CPU-hours per month for Institutional Computing. Applications include astrophysics, discrete event simulations, cosmology, quantum chemistry, plasma physics, black hole research and others. The Lab is pioneering the practice of using a highly scalable, centralized shared storage resource to eliminate the requirements of local disks on each compute node, thereby eliminating reliability problems. This in turn reduces maintenance and lowers total cost of ownership. LANL evaluated the full space of network-attached storage (NAS) and storage area networks (SAN) products and ultimately chose Panasas to support the Pink supercomputer.
"A highly scalable, shared file system was key to completing our diskless cluster," said Ron Minnich, team leader of cluster research at Los Alamos. "Panasas came in with an architecture and a product that enabled us to meet all of the objectives."
By combining a parallel file system with object-based storage, the Panasas Storage Cluster delivers scalable capacity and bandwidth in a single, seamless namespace. The integrated hardware/software platform enables customers to break the bottleneck inherent in legacy network storage systems to accelerate time to results with clustered storage for Linux. The Panasas storage architecture has the ability to support future generations of LANL's Pink supercomputer. This includes supporting multiple clusters from a single centralized storage pool.
"A wave of real-world applications that use Linux cluster computing is being developed in technical and commercial organizations today, but the full benefits of these solutions will only be recognized when the storage bottleneck is eliminated," said Victor Perez, chief executive officer at Panasas. "Panasas is reshaping the network storage paradigm by driving out costs and complexities associated with legacy storage."
About Los Alamos National Laboratory
Los Alamos National Laboratory is operated by the University of California for the National Nuclear Security Administration of the U.S. Department of Energy and works in partnership with NNSA's Sandia and Lawrence Livermore national laboratories to support NNSA in its mission. Los Alamos enhances global security by ensuring the safety and reliability of the U.S. nuclear deterrent, developing technologies to reduce threats from weapons of mass destruction, and solving problems related to defense, energy, environment, infrastructure, health and national security concerns. For more information on the Pink software, see www.clustermatic.org.
Panasas, Inc. helps companies accelerate the speed and accuracy of their business decisions, leading to real world breakthroughs that improve people's lives. Panasas enables customers to maximize the benefits of Linux clusters by breaking down the storage bottleneck created by legacy network storage technologies. Through the delivery of the company's Storage Cluster Platform, which combines industry-standard hardware with the company's ActiveScale File System and professional services, the company has become the established leader in object-based, clustered storage. Panasas' headquarters are in Fremont, CA with development facilities in Pittsburgh, PA and Houston, TX.