Statistical Machine Learning Makes Automatic Control Practical for Internet Datacenters
Peter Bodik, Rean Griffith, Charles Sutton, Armando Fox, Michael I. Jordan and David A. Patterson
In: Workshop on Hot Topics in Cloud Computing(2009).
Horizontally-scalable Internet services on clusters of commodity computers appear to be a great fit for automatic control: there is a target output (service-level agreement), observed output (actual latency), and gain controller (adjusting the number of servers). Yet few datacenters are automated this way in practice, due in part to well-founded skepticism about whether the sim- ple models often used in the research literature can cap- ture complex real-life workload/performance relationships and keep up with changing conditions that might invalidate the models. We argue that these shortcomings can be fixed by importing modeling, control, and anal- ysis techniques from statistics and machine learning. In particular, we apply rich statistical models of the applica- tion’s performance, simulation-based methods for find- ing an optimal control policy, and change-point methods to find abrupt changes in performance. Preliminary re- sults running a Web 2.0 benchmark application driven by real workload traces on Amazon’s EC2 cloud show that our method can effectively control the number of servers, even in the face of performance anomalies.