July 10, 2013
BEAVERTON, Ore., July 10 -- Open Scalable File Systems (OpenSFS), the premier non-profit organization supporting and coordinating the High Performance Computing (HPC) open source file system community, is announcing the general availability of Lustre 2.4 file system. The new set of features extends the capabilities of Lustre significantly, signaling Lustre's growing usage beyond traditional HPC environments.
As with previous releases, OpenSFS was deeply involved in funding major enhancements, sourcing and defining requirements, and supporting community vetting and testing activities.
"The Lustre 2.4 release includes both features that are long-requested and ones that further build the foundation as a key HPC and Big Data technology. OpenSFS is proud to continue to provide strong financial support for the Lustre file system," said Galen Shipman, OpenSFS Chairman. "This new release will further enable Lustre to tackle a wide variety of challenges, most notably metadata intensive Big Data workloads. These workloads are increasingly prevalent across a variety of domains such as social media, oil and gas exploration, genomics, and traditional HPC, where tens, hundreds of thousands, or even millions of files must be processed concurrently. This is a big step forward for Lustre."
Lustre is a parallel distributed file system for large-scale cluster computing utilized today by 7 out of 10 of the TOP10 supercomputing sites and over 60% of the TOP100. OpenSFS continues to play a pivotal role in Lustre roadmap discussions and feature releases. OpenSFS sponsors development of new features through the OpenSFS Technical Working Group (TWG) and coordinates community development and release discussions through the OpenSFS Community Development Working Group (CDWG). Moving beyond this current release, OpenSFS's request for proposal (RFP) W4570, for example, will facilitate Lustre file system feature development, parallel file system tools development, and address Lustre technical debt and parallel file system incubators.
Lustre 2.4 Major Features
Open Scalable File Systems is the premier participant-supported, vendor-neutral, and non-profit organization supporting and coordinating the High Performance Computing (HPC) open source file system community. We aggregate community resources as the center of collaborative activities. Our technical Working Groups bring in experts from many fields and backgrounds to contribute to roadmap discussions. OpenSFS-sponsored events create opportunities to network directly with the smartest open source file system engineers and business leaders. Our membership provides leverage for messaging and awareness. http://www.opensfs.org/
Source: Open Scalable File Systems
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?