Seagate high-end storage update.
-
Tom's Hardware Seagate announced the ClusterStor 300N at Supercomputing 2016 as its solution to the storage bottleneck. The first step to jumping the storage hurdle is to employ the correct high-performance file system, so Seagate offers the Lustre parallel distributed file system and Spectrum Scale (licensed GPFS Global Parallel File System from IBM), which are two of the most popular HPC filesystems.
-
We looked at Lustre back in 2006 but found it to be lacking. Went with other technologies at the time. Gluster was the answer to Lustre for much of the world.
-
Press release:
Seagate Technology plc (NASDAQ: STX) today introduced the ClusterStor 300N storage system with Nytro Intelligent I/O Manager, the newest addition to its family of scale-out storage systems for high-performance computing (HPC) and the first with a flash cache accelerator.
Powered by the software-based Nytro Intelligent I/O Manager, the ClusterStor 300N seamlessly runs multiple mixed workloads simultaneously on the same storage platform, eliminating performance bottlenecks that can result when data demands outpace what the existing storage architecture can accommodate. As a result, organizations can use it to automatically support multiple applications that generate a diverse range of I/O workloads on the same storage platform without negatively impacting performance. It’s particularly suitable for the kinds of mixed and unpredictable workloads found in many of today’s most demanding, data-intensive HPC applications like seismic processing, financial transition modeling, machine learning, geospatial intelligence and fluid dynamics.
Ideal for organizations seeking both peak performance and cost efficiency when managing large data sets at scale with unpredictable workloads, the ClusterStor 300N represents the convergence of Seagate’s market leading enterprise class hard drives, innovative solid state designs and the industry’s most sophisticated system software within a platform purpose built to help organizations manage and move massive amounts of critical data while maintaining workload efficiency and minimizing the cost per terabyte. The Nytro Intelligent I/O Manager software delivers up to 1,000 percent input/output workload acceleration over traditional HPC storage systems and can quickly scale to accommodate any workload at any time.
“Maximizing value of data in the kinds of extraordinary environments represented by supercomputing is all about being able to handle extreme, unpredictable storage bandwidth and capacity needs at scale,” said Ken Claffey, vice president and general manager, Seagate HPC systems business. “Seagate’s ClusterStor 300N expands on our proven, engineered systems approach that delivers performance efficiency and value for HPC environments of any size, using a hybrid technology architecture to handle tough workloads at a fraction of the cost of all-flash approaches.”
The ClusterStor 300N is architected specifically as a common platform for both the ClusterStor, Lustre and IBM Spectrum Scale storage systems as the L300N and G300N, respectively.
“With a long track record of mission-critical HPC deployments and support, Atos Extreme Computing is excited to extend its support to Seagate’s new range of Nytro Intelligent I/O Manager -based ClusterStor appliances,” said Eric Eppe, head of products and solutions, Extreme Computing, Atos. “We believe Seagate’s 300N appliance will help our HPC customers solve their most data intensive workloads and data hierarchy issues in a comprehensive, yet more efficient way.”
“The 300N offers the density, extreme bandwidth, low latency and simplified manageability that our customers demand in their HPC storage environments today,” said Mike Vildibill, vice president, HPC Storage, Hewlett Packard Enterprise. “New storage innovations like the ClusterStor 300N are critical for answering these demands and maintaining a high level of performance across a wide range of workloads.”
The 300N will be widely available in January 2017. Learn more at Seagate’s booth #1209 at the Supercomputing 2016 conference in Salt Lake City, Utah, Nov. 14-17. Other Seagate technology demonstrations at the event will include the highest density 720 terabyte, two-rack unit (RU) Lustre storage system technology configuration, making it possible to build the world's first 15 petabyte, 42RU system, as well as a single NVMe over a Fabric, 24-drive all flash array shared storage system delivering 4.8 million IOPS with single-digit microsecond latency.
The ClusterStor family architecture is built on Seagate’s field-proven, enterprise-class hard drives and high-performance parallel file systems such as Lustre and IBM Spectrum Scale. Combining superior performance with ultra-efficient scalability, the ClusterStor family includes the new ClusterStor L300N and G300N, as well as the ClusterStor A200 Active Archive, ClusterStor L300, ClusterStor G200, ClusterStor 9000, ClusterStor 1500, ClusterStor Secure Data Appliance and Hadoop Workflow Accelerator for ClusterStor’s architecture.