Blogs

Read how flash storage is different and how you can test performance more accurately

Load DynamiX has published a performance testing methodology white paper for All-Flash-Arrays (AFAs) in collaboration with the industry’s flash leaders at the storage vendors and well-known industry analysts.

FlashMethTestImageThe white paper can be found here

Performance testing is important if you have these kinds of questions:

  • Can I improve application performance with flash? If so, by how much?
  • Can I afford the performance improvement? Will dedupe / compression reduce the effective $/GBwithout substantially impacting performance?
  • Will the total cost of ownership be reduced by leveraging deduplication / compression, increased storage throughput, data reduction, reduced power requirements, reduced cooling costs, and reduced VM licensing costs due to greater storage throughput efficiency? And how will all this impact performance?
  • How do I select the best vendor or product?
  • Which of my workloads will run best on AFAs?
  • How will storage behave when it reaches its performance limits?
  • For which workloads should I use an AFA or a hybrid flash array (HFA)?

No one disagrees that the most accurate way to test performance is in a production environment — but it’s simply not possible. The next best thing is a realistic, scalable test in a lab environment. Storage engineers have had decades to refine HDD-based array testing, compared to only a short time to learn about flash storage.  That’s where we come in.

In the white paper, we discuss how flash is different than HDD arrays and what you should do differently to test them. We cover compression and deduplication, workload profiles, scale, preconditioning, and much more. And we also detail the specific steps to take to ensure accurate and meaningful results.

With a robust test and validation process in place, storage engineers and architects can optimally select and configure AFA products for their workloads with potentially considerable impact on both the performance and the cost of their production solutions.

By following testing best practices in the lab, AFA product selection and configuration becomes a mathematical exercise, not a guessing game.

by
Jim Bahn
Sr. Director, Product Marketing