Energy-Efficient Server Clusters

This paper evaluates five policies for cluster-wide power management in server farms. The policies employ various combinations of dynamic voltage scaling and node vary-on/vary-off (VOVO) to reduce the aggregate power consumption of a server cluster during periods of reduced workload. In terms of their implementation complexity, the policies fall into three categories, and we explain the potential benefit of each policy in terms of its implementation cost. We evaluate the policies using a validated simulator that calculates the energy usage and response times of a Web server cluster serving traces culled from real-life Web server workloads.

Our results show that a relatively simple policy of independent dynamic voltage scaling on each server node can achieve savings ranging up to 29% and is competitive with more complex schemes for some workloads. A policy that brings node online and takes them offline depending on the workload intensity also produces significant savings up to 42%. However, in some cases, we find that independent dynamic voltage scaling provides more energy savings and a simpler implementation than VOVO. The most savings are obtained by using a co-ordinated voltage scaling policy in conjunction with VOVO. This policy provides up to 18% more savings than just using VOVO in isolation. All five policies maintain server response times within acceptable norms.

PDF (123 KBytes)

Back to publications page