Browsing Tag Lustre

Live from HPCS – Canada

By Peter Bojanic | May 1, 2012 at 4:08 pm | No comments

Hello from Vancouver! I am here at the High Performance Computing Symposium as part of BCNET & HPCS 2012 which is Canada’s premier HPC forum.  The three day Symposium looks to be an exciting one with close to 500 high profile delegates from various disciplines within the...

Posted in: Storage Insights

Storage Performance: Block vs. File System

By Torben Kling Petersen | November 11, 2011 at 7:43 pm | No comments

File system performance is often a major component of overall HPC system performance, and is heavily dependent on the nature of the application(s) generating the load. To achieve optimal performance, the underlying file system configuration must be balanced to match the...

Posted in: Storage Insights

Xyratex Releases Lustre Migrator Tool

By Michael Connolly | November 3, 2011 at 4:56 pm | No comments

In our continued commitment and support of the Lustre® community, we have announced and released, in mid-October, a Lustre migrator tool that is available for use, licensed under the GPL 2.0, to the entire Lustre community. The Xyratex migrator tool converts Lustre file system...

Posted in: Storage Insights

Why Lustre?

By Torben Kling Petersen | October 25, 2011 at 5:29 pm | No comments

Lustre is not the only scalable parallel file system in the HPC world but, during it’s 10 year lifespan, it still dominates in eight out of the top ten HPC systems in the world and is in more than 70% of the Top500.  Lustre is open source so it is not tied to a single vendor...

Posted in: Storage Insights

Benefits of Parallel File Systems for HPC Performance

By John Fragalla | October 14, 2011 at 1:53 pm | No comments

When architecting HPC storage solutions, there are really two options to look at:  a network file system (NFS) solution or a parallel file system.  For years NFS was the dominant protocol for sharing data between compute nodes because it was free and relatively...

Posted in: Storage Insights

The Exascale Storage Forum at the 2011 IEEE Cluster Meeting

By Peter Braam | October 4, 2011 at 3:02 pm | No comments

I was recently on a panel discussing the status of exascale storage today.   The discussion was aligned on the 10PF, 100PF and 1EF boundaries.   For 10PF, there's little to say, Lustre is running on 9 of the top 10 systems, including the 8PF Riken system. Much refinement is...

Posted in: Storage Insights

Live From the HPC User Forum

By Peter Bojanic | September 6, 2011 at 3:31 pm | No comments

Hello from San Diego! This week looks to be a busy one for the HPC community. With so much happening in this industry, it’s hard to stay up to date with all of the recent installations, new technologies and industry initiatives. That’s why I like participating in events like...

Posted in: Storage Insights

Yearning for Simpler Times

By Chris Bloxham | July 13, 2011 at 3:45 pm | No comments

Why does storage for HPC have to be so hard? Building HPC data storage using traditional servers, storage systems and network fabrics (SAN) gets in the way of simplicity, performance and resiliency for those that just care about getting to their research results. For me,...

Posted in: Storage Insights

Lustre Users Group (LUG) was a fantastic event!

By Ken Claffey | April 19, 2011 at 3:20 pm | No comments

The Orlando LUG was probably the most productive event that I’ve attended recently. The community turned out in large numbers (Yes) for this year’s meeting and they were very active in helping to set the foundation for the “post Oracle” era of Lustre. Xyratex was happy...

Posted in: Storage Insights

Live From The Lustre User Group

By Ken Claffey | April 12, 2011 at 1:51 pm | No comments

I spent yesterday at the Lustre User Group meeting in Orlando and I couldn’t help but notice the change in the atmosphere. Last year’s meeting had a dark cloud of uncertainty hovering over it versus the sense of stability that has surrounded this year’s meeting. Who...

Posted in: Storage Insights

© 2012 Xyratex. All rights reserved.