Seagate ClusterStor A200 Tiered Archive Storage System for HPC

Seagate Technology plc introduced ClusterStor A200, a tiered archive storage system for HPC.

The A200 helps reduce storage and operational costs by up to 50% compared to tier-one storage platforms.

It was designed to complement the rest of ClusterStor family of scale-out storage systems. It allows customers to non-disruptively migrate designated data off of the performance-optimized, primary storage tiers while keeping it online for fast retrieval. This avoids a common problem in shared HPC environments where the organization is forced to choose between having all of the data available to make the best analysis versus the time required to retrieve data from tape. Performance of the primary storage is often improved by migrating data and freeing up space for more efficient data layout. The pre-configured A200 solution includes an automatic policy-driven HSM system and near limitless scale-out capacity.

“The A200 is designed to be the perfect complement to our high performance ClusterStor Lustre and IBM Spectrum Scale engineered systems,” said Ken Claffey, VP and GM, HPC systems business, Seagate. “It balances performance while also delivering a system that is optimized for the lowest capex and opex for active archive applications. Many critical HPC systems need to go back and analyze valuable data that’s already been archived, but our customers want these large archives to be online with massive data sets available instantly. ClusterStor A200 is a purpose-built solution to help enable storage tiering and end-to-end workflow in HPC environments.“

The ClusterStor A200 was engineered to meet customers’ most demanding HPC needs in fields such as weather, life sciences, oil and gas, financial services, pharmaceuticals, and geospatial intelligence.

The A200 consists of up to seven scalable storage units per rack with additional storage units and racks easily added to the storage pool, and a highly available ClusterStor management unit. The A200 system also includes a comprehensive management system with a single, easy-to-use administrator interface. The A200 system implements the 3rd generation ClusterStor erasure coding to provide unparalleled data and disaster protection with up to 11 nines of durability. This new and enhanced erasure code is network-based allowing it to use the resources of the entire system to achieve extremely fast rebuilds of failed drives, improving availability while maximizing the amount of useable storage delivered to the customer’s applications. To further enhance the durability of data in the A200 system, the ClusterStor erasure code uses a unique mechanism to prioritize the most critical data elements to rebuild, substantially improving the time required to return the system to maximum data protection.

The ClusterStor family architecture is built on company’s enterprise storage platforms and high performance parallel file systems such as Lustre and IBM Spectrum Scale. Combining performance with efficient scalability, the ClusterStor family includes ClusterStor A200, ClusterStor L300, ClusterStor G200, ClusterStor 9000, ClusterStor 1500, ClusterStor Secure Data Appliance and Hadoop Workflow Accelerator for ClusterStor’s architecture.

ClusterStor A200 will be available in calendar Q1 2016.