Xyratex Enhances ClusterStor OS for HPC Storage
New performance, capacity, management and security capabilities
This is a Press Release edited by StorageNewsletter.com on June 24, 2013 at 3:17 pmXyratex Ltd has released version 1.3 of the operating system software for its ClusterStor 6000 HPC storage solution.
The enhancements in the new version will deliver added performance, capacity, security and fault tolerance to customers, making a storage solution more versatile and powerful.
Specifically, the new enhancements usher in:
- The introduction of an expansion storage unit (ESU). The ESU is an optional building block that expands the number of drives of a single scalable storage unit (SSU) from 84 to 168, providing higher capacity scale-out increments. This allows ClusterStor 6000 users the flexibility to scale-out their performance linearly at much higher capacity ratios.
- Support of 4TB SAS disk drives within ClusterStor storage systems, enabling even higher capacity with the same fast performance. The ClusterStor 6000 now can provide up to 256TB of usable file system capacity in a single SSU with 4TB drives, or up to 512TB of usable file system capacity in an SSU-ESU pair.
- Enhanced security and performance through: a new hardware-assisted CRC-32 feature that leverages Xeon processor instruction sets on each SSU embedded server module to ensure data integrity over clustered data storage networks and drive a substantial boost to system performance through increased efficiency; and additional compatibility with additional user authentication systems.
- Improved file performance with the introduction of wide stripe, which increases the number of SSUs and ESUs a single file system or individual file can span. Wide striping expands the number of SSUs and ESUs from 40 (160 object storage targets) to 500 (2000 object storage targets).
- Higher availability for ClusterStor Manager. The fault tolerance in ClusterStor management services is enhanced through automated failover capabilities which ensure the survival of storage cluster management services even in the event of a management node failing.
"We’re confident that these significant enhancements will only add to the market leadership of our ClusterStor data storage systems, and the tremendous value users receive from them," said Ken Claffey, SVP of the ClusterStor business, Xyratex. "Today, in collaboration with our partners, we’re helping end users achieve best-in-class performance, reliability and availability – including implementing the fastest data storage system in the world. Now we can offer users even more performance, improved scalability, security and fault tolerance."
"By using the performance-enhancing instruction sets built into the Intel Xeon processor such as in the CRC-32 function, Xyratex was able to add this key data integrity feature to their product and provide a significantly higher level of performance over what could be achieved without taking advantage of the processor’s capabilities," said Bev Crair, GM of the storage division, Intel Corp.
"Xyratex has made a significant investment in delivering ClusterStor to the benefit of end users, and with software version 1.3 of the ClusterStor operating system to make the systems even more powerful and easier to use," said Peter Foulkes, research director for servers, virtualization and cloud computing, 451 Research. "Xyratex has once again proved itself as a storage technology provider that is increasingly relevant to HPC and big data users, because of its ability to deliver market-leading capabilities and value at a compelling price."
ClusterStor delivers a new standard in file system performance, scalability and efficiency. Its scale-out clustered file system architecture brings together what were previously discrete server, network and storage platforms with their own separate software layers, into a single integrated high performance storage solution. This approach enables the solution to scale both performance and capacity while reducing space, power and administrative overhead.