Autonomic energy management of multi-tier clustered applications

Nowadays, medium or large-scale distributed infrastruc-tures such as clusters and grids are widely used to host var-ious kinds of applications (e.g. web servers or scientific ap-plications). Power consumption is becoming a major chal-lenge for most organizations that run these infrastructures. Many studies show that they are not used at their full ca-pacity and that there are therefore a huge source of wasted power. Autonomic management systems have been introduced in order to dynamically adapt software infrastructures accord-ing to runtime conditions. They provide support to deploy, configure, monitor, and repair applications in such environ-ments. In this paper, we report our experiments in using Tune- an autonomic management system- to provide energy aware management for a clustered J2EE application. We use Tune to dynamically adapt the degree of replication of the J2EE tiers in the cluster, and to dynamically turn cluster nodes on- to handle the load when it raises up- and off- to save power under lighter load. 1