Contact Sales

RSS

Parallel Storage

HPC ≠ Complex and Unreliable!

Barbara Murphy

CMO

Utah State University (USU) is bucking the trend of many universities who are leveraging the high performance computing (HPC) facilities at national laboratories for research, paying on a per-use basis, rather than maintaining their own HPC centers.  Using national labs could potentially eliminate on-going capital equipment investment along with the associated operating and maintenance expenses, and is a good way to gain experience in HPC.  However, as the system demand grows, the work of planning research around available cycles on other systems brings its own set of challenges.&

Hadoop in the Enterprise?

Barbara Murphy

CMO

I recently attended a panel event at the Churchill Club in Silicon Valley (http://www.churchillclub.org). “The Elephant in the Enterprise: What Role Will Hadoop Play?” certainly packed the house. The panel included users and vendors from Facebook, Cloudera, Oracle, MapR, and Metamarkets, each providing very different perspectives on Hadoop’s readiness for the enterprise. . It was interesting to compare the user perspective “…it is no way ready for primetime,” with the vendor perspective being “…of course it’s ready!”

Big Finance

Barbara Murphy

CMO

Last year I wrote a blog post that showed how the lack of parallelism in computing was a limiter to innovation.  My post was inspired by a technology article I read in the Economist magazine – http://www.panasas.com/blog/parallelism-goes-mainstream.

Garth Gibson's History of RAID, Part I -- "Thinking the RAID Way"

Admin

Panasas Marketing

It was recently announced that Panasas co-founder and chief scientist, Dr. Garth Gibson, has won the 2012 Jean-Claude Laprie Award in Dependable Computing for his pioneering work with RAID, including his co-authorship of the influential “Berkeley RAID Paper” – A Case or Redundant Arrays of Inexpensive Disks (RAID).

The Last Bottleneck: How Parallel I/O Can Attenuate Amdahl's Law

Admin

Panasas Marketing

Categories: 

Director of worldwide systems engineering, Rex Tanakit, gives his thoughts on parallel computing's migration to the mainstream in this blog post:

2011 Recap

Faye Pairman

President and CEO

2011 was a year of investing and building for Panasas as we prepared for continued success in the coming year. I want to take the time, before the year winds down to thank our employees, our partners, and most importantly our customers for a great 2011 and in so doing, I would like to remind all of us of some of our 2011 highlights:

Garth Gibson on Solid State Storage

Admin

Panasas Marketing

This is part two in a Q&A series with Panasas founder and CTO, Dr. Garth Gibson. He was recently asked by a large storage research center to comment on various HPC storage topics. Garth’s thoughts on solid state technology were captured in the following exchange.

Panasas Parallel File System and RAID

Brent Welch

CTO

In my last post I talked about how the Panasas parallel file system (PanFS) achieves extreme performance for big data sets. It also provides redundancy without the need for hardware RAID controllers. In the attached video, Garth Gibson, Panasas founder and CTO, digs deep into the specifics of file system RAID and how PanFS delivers redundancy as part of the file system itself.

Get Parallel – Extreme Performance for Extremely Big Data

Brent Welch

CTO

In 2008 the first computer broke the petascale barrier, allowing a supercomputer to exceed 1015 operations per second. The Panasas parallel file system was instrumental in accomplishing this major milestone, achieving extreme performance for big data sets.

The Benefits of Object RAID

Brent Welch

CTO

Traditional RAID is designed to protect whole disks with block-levelredundancy.  An array of disks is treated as a RAID group, or protection domain, that can tolerate one or more failures and still recover a failed disk by the redundancy encoded on other drives.  The RAID recovery requires reading all the surviving blocks on the other disks in the RAID group to recompute blocks lost on the failed disk.  As disks have increased capacity by 40% to 100% per year, their bandwidth has not increased substantially. 

Pages

Subscribe to Parallel Storage