Sun buys CFS (aka lustre)

Sun Microsystens announced a definitive agreement pursuant to which Sun will acquire the majority of Cluster File Systems, Inc.'s intellectual property and business assets, including the Lustre File System. By acquiring Cluster File Systems, Inc., the leading parallel file system provider, Sun intends to add support for Solaris Operating System (Solaris OS) on Lustre and plans to continue enhancing Lustre on Linux and Solaris OS across multi vendor hardware platforms. As previously announced in July 2007, Sun also plans to deliver Lustre servers on top of Sun's industry-leading open source Solaris ZFS solution, which is one of the fastest growing storage virtualization technology in the marketplace.

Wow. That's not exactly some news that I can say I am comfortable with. While I have not been a fan of CFS' rate of development or, in general their file system, they have been at least a competitor with IBM's GPFS. There are a few others that are competitive here, but not many. CFS and IBM are the big dogs, so to speak. Since my work is in center wide - and sometimes wide area - file systems, I definitely have some keen interest to see how this plays out.

High End Computing File Systems and I/O Workshop 2007

HECIWG Executive Summary

The HECIWG is chartered by the The National Science and Technology Council's Subcommittee on Networking and Information Technology Research and Development (NITRD). The purpose of the IWG is to coordinate high-end computing (HEC) programs, budgets and policy recommendations. This includes identifying and integrating requirements, conducting joint program planning and devloping joint strategies for the HEC programs conducted by agencies that participate in the NITRD Program. A complete description of the HEC IWG can be found at NITRD's website.

HEC File Systems and I/O (HEC FSIO) Background

The need for immense and rapidly increasing scale in scientific computation drives the need for rapidly increasing scale in storage for scientific processing. Individual storage devices are rapidly getting denser while their bandwidth is not growing at the same pace. In the past several years, initial research into highly scalable file systems, high level Input/Output (I/O) libraries, and I/O middleware was done to provide some solutions to the problems that arise from massively parallel storage. To help plan for the research needs in the area of File Systems and I/O, the inter-government-agency document titled "HPC File Systems and Scalable I/O: Suggested Research and Development Topics for the Fiscal 2005-2009 Time Frame" was published which led the HECIWG to designate this area (FSIO) as a national focus area starting in FY06.

HEC FSIO Purpose

The HEC FSIO was created to advise the HECIWG in coordination of government R&D funding in HEC File Systems and I/O area so that the government's investment in this area of HEC is well spent, reduce gaps and overlaps. We are attempting to enable more and better R&D, and pass along the knowledge to the next generation.

Take a look. There's some good and interesting chewsy bits in there.