|
With the massive increase in the number of desktop users, high-end workstations, application servers, High Performance Computing (HPC) and compute cluster nodes over the last decade, conventional network attached storage (NAS) solutions have been challenged to meet the resulting acceleration in customer performance and scaling requirements. While file server vendors have offered systems with faster CPUs, including the move to multiple cores, and other off-the-shelf components as they become available, bandwidth and IO demands have far outpaced the ability of these CPU-based appliances to keep up. To meet increased performance and capacity requirements, companies have been forced to deploy multiple, siloed, NAS appliances– reducing the benefit of NAS, decentralizing data and complicating storage management.
Many customers looking for a solution to this performance deficit turned to storage area network (SAN) implementations. However, there are challenges with SANs that aren’t present with NAS. First, SANs have a high infrastructure cost. Adding one or two expensive Fibre Channel HBAs and associated switch ports for each high-end workstation, application and database server, and cluster node, is an expensive proposition compared to using existing Ethernet ports. Expensive license fees, maintenance costs and complexity add to the financial burden. By far the biggest challenge to customers is that a SAN alone does not provide the standards-based shared file access needed for simple data management.
Another solution that some customers are beginning to look at is the concept of storage grids. For conventional NAS vendors that cannot scale performance or capacity, this strategy is not an option, but, instead, a necessity, as single systems are not capable of scaling to meet today’s enterprise infrastructure requirements. Although storage-grids are interesting, they are far from ready for prime time. Consider the rise of compute-clusters as an allegory. In the summer of 1994, Thomas Sterling and Don Becker, working as contractors to NASA, built a clustered computer consisting of 16 DX4 processors connected by channel bonded Ethernet. They called their machine Beowulf. Now, years later, compute-clusters are commonly used in research and are gaining wider acceptance in commercial enterprises. The key to this acceptance is that the complex software that ties compute-clusters together and distributes tasks to the nodes has finally begun to mature to a point where companies can rely upon them for stable services.
Some aspects of compute-clusters translate directly to storage-grids; however, there are enormous complexities that are introduced as well. File locking, cache coherency, client-side caching and many other aspects of sharing a file system make using storage-grids a daunting task. This may be solved over time, but as with compute-clusters, it will take a significant amount of time for storage-grids to mature. The Internet Engineering Task Force (IETF) has proposed a new standard called Parallel NFS (pNFS). pNFS is an extension to NFSv4.1 and will help focus the industry towards a standards-based solution. This approach perfectly matches BlueArc’s commitment to support standards-based protocols and methods, while taking advantage of its unique hardware architecture for acceleration of data flow. Moreover, BlueArc will be able to deliver a significantly less complex solution by keeping the node count low, while still achieving the unmatched performance. Further discussion of storage-grids will be covered in a separate paper; however, BlueArc is committed to providing the fastest nodes for storage grids, ensuring reduced complexity and cost, while delivering best in class performance and scalability.
Having assessed the limitations of scaling an individual CPU-based NAS server, BlueArc chose, in 1999, to take a fresh approach to the problem, with the fundamental belief that file services could be accelerated using hardwarebased state machines and massive data path parallelization, in the same way Ethernet and TCP/IP had been accelerated by switch and router vendors. The network vendors moved from software-based solutions to hardwareaccelerated solutions, to speed up packet flow processing. It seemed logical that file services should follow this same evolution, and an evolutionary new design would be required to attain the same benefits as experienced in the networking.
BlueArc’s Founding Design Principles
BlueArc had the unique technical acumen to be able to build a new platform for data access acceleration, but this is only one aspect of creating a world-class network storage offering. Our key design principles - keeping it simple, maintaining a standards-based approach, and ensuring data availability while enabling significant increases in performance and capacity – have guided BlueArc’s hardware and firmware design through several generations of hardware accelerating NAS systems. The BlueArc Titan Architecture has evolved into the pinnacle of enterprise class file sharing.
|
