Hardware

When growing capacity and power in the data center, the architectural trade-offs between server scale-up vs. scale-out continue to be debated. Both approaches are valid: scale-out adds multiple, smaller servers running in a distributed computing model, while scale-up adds fewer, more powerful servers that are capable of running larger workloads.

Real-time analytic processing often involves substantially large datasets, well beyond what can be cost-effectively accommodated in memory. The next generation of Flash memory technologies offer not just improvement in price/performance over disk, but when used as a RAM extension, they can also offer substantial cost-reduction without an equivalent degradation in performance.