Information will be the most valuable resource in the 21st century. Operating on large volumes of diverse data sources to get the right actionable insights at the right time presents new challenges and opportunities for system design. Addressing these opportunities requires a rethinking of future server and data center design—with a datacentric focus across both hardware and software. Here, we’ve presented a brief introduction to some recent research activities in this exciting emerging area, with a specific focus on system architecture and systems software.
With the rise of Big Data and increasing emphasis on data-intensive computing, you may be wondering how the tape vendors are doing. Well, very well, thank you, as evidenced by Spectra Logic’s announcement that that the company installed more than half an exabyte of tape storage capacity in the past six months alone. With revenue up 9 percent year-over-year, the company has a very bullish outlook indeed.
Our financial strength combined with strong growth in the file archive market is enabling us to invest significantly in R&D, which will be reflected in a strong slate of new products and technologies this coming year. In fact, over the next 12 months we plan to launch a large number of new data storage products – more than were released in the past five years combined,” said Nathan Thompson, Spectra Logic’s chief executive officer. “The value of tape technology and its essential role in today’s modern data centers is indisputable for both traditional backup as well as the tape-based file archive market. This value is recognized and embraced by leading organizations worldwide – and is reflected in Spectra Logic’s consistent growth and momentum.”
In this slidecast, Jeff Denworth from DDN describes the company’s new hScalar storage system — the World’s First Enterprise Apache Hadoop Appliance.
DDN has developed a Hadoop solution that is all about time to value: It simplifies rollout so that enterprises can get up and running more quickly, provides typical DDN performance to accelerate data processing, and reduces the amount of time needed to maintain a Hadoop solution.” said Dave Vellante, Chief Research Officer, Wikibon.org. “For enterprises with a deluge of data but a limited IT budget, the DDN hScaler appliance should be on the short list of potential solutions.”
The conference will focus on the following topics: Progress of Exascale in the European Union, high-performance interconnects, Accelerators and Parallel I/O, communication libraries (MPI, SHMEM, PGAS), GPU computing (CUDA, OpenCL) Big Data, advanced topics / technologies / development including server and storage systems, and hands-on clustering, network, troubleshooting, tuning, optimizations. The conference is open to the public and will bring together system managers, researchers, developers, computational scientists and industry affiliates.
Having been to this event several times, I can tell you that Lugano is one of the most beautiful towns in the world. It’s a solid three-day workshop, and this year they’ll be treating attendees to a boat trip on lake Lugano with an on-board apero and dinner.
Today Xyratex announced that the company has acquired the original Lustre trademark, logo, website and associated intellectual property from Oracle, and will assume responsibility for providing support to Lustre customers going forward. The company say it plans to advance the global Lustre portfolio by supporting the community-oriented development of Lustre as an open source file system and continuing to work in conjunction with the broader community to help chart the best path forward for this key technology.
Lustre is a powerful open source file system, and Xyratex strongly believes that all members of the Lustre community need to continue to play a part in the evolution of the code and the benefits it delivers over the long term,” said Steve Barber, CEO of Xyratex. “We want to ensure that current Lustre customers get the best possible feature roadmap and support, and we intend to engage the entire community to advance the Lustre technology. We also appreciate Oracle’s support of Lustre, and their efforts to ensure the long-term success of the technology.”
From this reporter’s perspective, this is really good news for the Lustre community. Oracle owned the Lustre assets since it acquired Sun Microsystems in 2010, and the company didn’t take kindly to organizations using the Lustre trademark in the past. Now with these assets in the hands of an active Lustre community member (Xyratex is a board-level sponsor of OpenSFS), one could say that Jack has effectively rescued the Open Source Goose from the mean old Giant.
OpenSFS actively supports the HPC open source file system community of which Xyratex is an active Member,” said Norm Morse, CEO at OpenSFS. “This acquisition gives Xyratex a great opportunity in concert with other members of the Lustre community to continue the stability needed to ensure Lustre remains a vital part of HPC going forward. We look forward to working with Xyratex in the future.”
With their ClusterStor products now being distributed by the likes of Cray, HP, and Dell, Xyratex is now well-positioned to move forward with their increasing focus on HPC and Big Data markets. Powered by Lustre, ClusterStor technology not only holds the title for world’s fastest file system at over 1 Terabyte/sec, they managed to accomplish that number with about half the storage devices of the next runner-up.
In this slidecast, Gary Tyreman from Univa discusses the new Univa Grid Engine for ARMv7 Release. As HPC and Big Data infrastructure design continues to converge, this platform could be a stepping stone to the future.
Driven by the demand for new datacenter services to support mobile and cloud computing, ARM will continue to gain in-roads into the datacenter server market because of the low-power and energy efficient design of SOC’s based on ARM’s technology”, said Karl Freund, VP Marketing at Calxeda. “As enterprises shift towards highly scalable solutions such as Calxeda, a key enabling technology is intelligent workload management – and we have partnered with Univa to provide our customers with a great solution.”
In this video, Amr Awadallah from Cloudera presents: Cloudera, Impala, and EDW Optimization.
Everyone knows that data volumes are growing exponentially. What’s not so clear is how to unlock the value it holds. The answer is Cloudera, the Platform for Big Data. With a single, integrated enterprise-class solution, Cloudera lets you efficiently query all of your data – structured and unstructured – and have a view beyond data sitting in relational databases. Equally important, Cloudera’s platform runs in real time, so you can work at the speed of thought as you build rapidly on deep insights, create competitive advantage and become truly data-driven.
In this video, Brent Gorda from Intel’s High Performance Data Division presents: The Future of Network-Based Storage. Gorda joined Intel in July 2012 as part of Intel’s acquisition of Whamcloud. Since then, Gorda’s team has continued to work on Lustre as well as conduct R&D on Darpa’s Fast Forward Storage & IO program.
In this video, John Fragalla from Xyratex presents: Architecting High Availability Lustre Storage with ClusterStor 6000.
ClusterStor 6000 is designed to support installations with linear performance scalability in less space, scaling from up to 6 gigabytes per second to installations providing 1 terabyte per second file system throughput, as well as linear data storage capacity from terabytes up to tens of petabytes.
