Click here for full text:
Adaptive Entitlement Control of Resource Containers on Shared Servers
Liu, Xue; Zhu, Xiaoyun; Singhal, Sharad; Arlitt, Martin
Keyword(s): utility computing; resource containers; resource entitlement; adaptive control
Abstract: In this paper, we describe the problem of designing online feedback control algorithms to dynamically adjust entitlement values for a resource container on a server shared by multiple applications. The goal is to quickly determine the minimum level of entitlement the container should receive in order for its hosted applications to achieve desired performance levels. Classic control theory is used as the foundation for both model identification and controller design. Specific implementation issues that affect the closed- loop system performance are discussed in detail, and a better implementation design is presented. A self- tuning adaptive controller is also presented to handle limited variations in the workload. All the controllers were implemented and evaluated on a testbed using the HP-UX PRM as the resource container technology and the Apache Web server as the hosted application inside the container. In all the experiments, our controller was able to quickly converge to the proper level of CPU entitlement to the Web server for it to track its performance target. By using our entitlement control system, shared servers can potentially reach much higher resource utilization while meeting service level objectives for the hosted applications under changing operating conditions.
Back to Index