Using MIMO feedback control to enforce policies for interrelated metrics with application to the Apache Web server

TLDR

Policy‑based management lets IT systems align with business needs, but administrators face an impedance mismatch when controlling Apache’s CPU and memory usage indirectly through tuning parameters, and prior feedback‑control work has largely ignored the interactions between multiple controls. This paper shows how multiple‑input, multiple‑output (MIMO) control theory can be used to enforce policies for interrelated metrics. The authors model Apache with a MIMO system that captures the interaction between KeepAlive and MaxClients, and use this model to design feedback controllers that can detect infeasible metric policies. MIMO control improves policy enforcement by balancing rapid metric convergence against sensitivity to random fluctuations.

Abstract

Policy-based management provides a means for IT systems to operate according to business needs. Unfortunately, there is often an "impedance mismatch" between the policies administrators want and the controls they are given. Consider the Apache Web server. Administrators want to control CPU and memory utilizations, but this must be done indirectly by manipulating tuning parameters such as MaxClients and KeepAlive. There has been much interest in using feedback control to bridge the impedance mismatch. However, these efforts have focused on a single metric that is manipulated by a single control and hence have not considered interactions between controls such as those that are common in computing systems. This paper shows how multiple-input, multiple-output (MIMO) control theory can be used to enforce policies for interrelated metrics. MIMO is used both to model the target system, Apache in our case, and to design feedback controllers. The MIMO model captures the interactions between KA and MC, and can be used to identify infeasible metric policies. In addition, MIMO control techniques can provide considerable benefit in handling trade-offs between speed of metric convergence and sensitivity to random fluctuations while enforcing the desired policies.