Case Study: The Case For Scale-Out NAS

There is a dark cloud looming in storage. Over the last decade, conventional storage platforms have been able to keep up with the demand for ever higher capacity systems at a lower cost per GB, however, the real specter on the horizon is severe and inevitable performance degradation. This degradation of performance is critical because most organizations rely on a scalable facility for servicing I/O to rapidly deliver information to aid in revenue generation. Indeed, resolving the storage I/O performance bottleneck becomes even more critical in a soft economy, when profits are the most elusive.

What's Causing the Storage I/O Bottleneck?

Multi-tenant workloads are at the heart of the problem. Multi-tenant workloads are also known as concurrent/aggregate workloads in which data is shared between multiple users or applications and accessed concurrently by multiple users of the same shared storage resource. These shared workloads and resources are no longer relegated to a few isolated companies whose performance demands are on the fringe of mainstream data center environments. In fact, any organization that is deploying a server virtualization project has by definition a multi-tenant workload demand.

There are three basic elements of performance in a data center; the processing power harnessed by servers, the network harnessed by switches and routers, and the storage which consists of the disks harnessed by SAN and NAS controllers also referred to as "NAS Heads". Each of these elements are under constant strain to keep up with the digital demands of their users. Servers and networks have kept pace through added performance and intelligently utilizing that performance, but storage has not kept pace and has become the bottleneck of the enterprise. Now this storage bottleneck has moved beyond being an IT problem and has created a perilous situation for the organization as a whole.