Xyratex Introduces ClusterStor 1500

A significant driver of growth in the overall HPC market is coming from the growing class of users that are adopting x86-based Linux compute clusters to run their digital simulation applications in parallel, utilizing ever greater compute power to solve complex problems sooner. This transition is happening across a wide range of industries, as simulation technology replaces traditional physical experimentation. The adoption of such clusters is creating a growing performance gap between the capabilities of the compute on one side and what the traditional storage systems can actually deliver on the other. This growing class of users requires department-level clusters encompassing several racks of compute and network infrastructure – and the kind of HPC storage solution that hasn’t been available in the market, until now.

“Departments within larger organizations or medium-sized enterprises today, especially in the commercial, academic and government sectors, represent an underserved market. They need high-performance and scalable storage solutions that are cost-efficient, easy to deploy and manage and reliable even under heavy workloads,” said Ken Claffey, senior vice president of the ClusterStor business at Xyratex. “Growth in this market segment is being driven by the increasing adoption of simulation applications in a wide range of industries from car and aircraft design to chemical interactions and financial modeling. Traditional enterprise storage systems are simply not designed to meet the performance needs of these applications, so we engineered and built the affordable and modular ClusterStor 1500 to bring the performance power of Lustre® to this underserved and growing market in the way that only ClusterStor can.”

ClusterStor 1500 is the newest member of the ClusterStor family of scale-out HPC storage solutions that delivers break-through industry performance and efficiency. ClusterStor 1500 features include:

•A unique architecture that brings together what were previously discrete server, network and storage platforms with their own separate software layers into a single integrated, modular, scale-out storage building block. This innovative approach enables the system to scale both performance and capacity while reducing administrative overhead.

•Reduced hardware complexity with increased reliability, availability and serviceability.

•The ability to scale performance from 1.25GB/s to 110GB/s and raw capacity from 42TB to 7.3PB.

•The Lustre file system, the industry’s most scalable and proven high performance open source parallel file system.

•Simplified deployment in hours, not weeks, allowing users to be productive and realize the value from their investment immediately.

•Proactive and comprehensive storage solution support, including assistance with setup, installation and performance optimization.

•ClusterStor Manager, a comprehensive system management application that consolidates management of the entire storage cluster infrastructure, RAID data protection layer, operating system and Lustre into a single-pane-of-glass, easy-to-use administrator interface.

“While HPC is most closely associated with Supercomputing, the second-largest segment of revenue in the overall HPC market (at roughly one-fourth of the whole) is department-level users. Their data storage challenges are significant and growing in importance as they move forward,” said Earl Joseph, program vice president of high-performance systems at IDC. “With the unique scale-out storage technology that is ClusterStor, Xyratex has solved many of the data storage challenges for some of the largest and most challenging deployments in the world. Xyratex and ClusterStor are well-positioned to do the same for the departmental segment of the HPC and Big Data markets.”

Trends in computation and Big Data have introduced HPC technologies to a wider variety of use cases, but introducing computation isn't enough. Even modest HPC clusters in genomic, energy exploration, digital manufacturing simulation or data analytics can drive large and growing amounts of data, and these use cases need adoptable, high-performance data management solutions to go with their compute clusters, said Addison Snell, CEO of Intersect360 Research. By packaging the performance and scalability characteristics of supercomputing-class data management into a more affordable and deployable form factor, the ClusterStor 1500 is well-positioned to lead the way in this market and to help usher in even more market demand and growth.

Today Lustre has a significant market share among the Top 100, however it becomes less prevalent in utilization beyond the Top 100, said Hugo Falter, COO of the ParTec Cluster Competence Center, GmbH and director of European Open File Systems (EOFS). The introduction of the ClusterStor 1500 is an excellent vehicle for Lustre to have a stronger foothold in the Top 500 and mainstream markets that require a more scalable and resilient file system and, as a result, effectively grow the Lustre Community.