A Workload Aware Storage Platform for Large Scale Computing Environments
Tremblay Benoit, Karol Kozubal, Wubin Li, Chakri Padala · 2016
Taking advantage of recent developments in Software Defined Storage and Cloud Computing, in this article we present our on-going effort, a Workload Aware Storage Platform (WASP), which aims to provide optimal storage backend assignment for given application storage workloads while minimizing or eliminating manual intervention. We identify four key challenges involved, i.e., characterization of storage workload and backend, and optimal mapping between storage workload and backend as well as the continuous optimization thereafter. We also present potential directions, including enabling techniques such as MAPE-K control, and deployment automation, to address these challenges. We believe that WASP potentially benefits not only the application with guaranteed SLAs, but also the cloud provider with improved resource utilization, eco-efficiency, and productivity.