SISO PIDF Controller in an Energy-efficient Multi-tier Web Server Cluster for E-commerce

In this paper we describe a simplified way to implement performance control in a multi-tier computing system designed for e-commerce applications. We show that the simpler SISO (Single Input Single Output) controller, rather than a more complex distributed or centralized MIMO (Multiple Input Multiple Output) controller, works well, regardless of the presence of multiple cluster nodes and multiple execution time deadlines. Our feedback control loop acts on the speed of all server nodes capable of dynamic voltage scaling (DVS), with QoS (Quality of Service) being the reference setpoint. By changing the speed, we change the position of the p-quantile of the tardiness probability distribution, a variable that enables to measure QoS indirectly. Then, the control variable will be the average tardiness, and the setpoint the tardiness value that will position this p-quantile at 1.0, value at which a request finishes exactly at the deadline. Doing so will guarantee that the QoS will be statistically p. We test this new Tardiness Quantile Metric (TQM) in a SISO PIDF control loop implemented in a multi-tier cluster. We use open software, commodity hardware, and a standardized e-commerce application to generate a workload close to the real world. The main contribution of this paper is to empirically show the robustness of the SISO controller, presenting a sensibility analysis of the four controller parameters: damping factor zeta, derivative filter factor beta, integral gain ki, and zero time constant tau.