Server workload analysis for power minimization using consolidation

Abstract

Server consolidation has emerged as a promising technique to reduce the energy costs of a data center. In this work, we present the first detailed analysis of an enterprise serverworkloadfrom the perspectiveof finding characteristics for consolidation. We observe significant potential for power savings if consolidation is performedusingoff-peakvaluesforapplicationdemand. However, these savings come up with associated risks due to consolidation, particularly when the correlation between applications is not considered. We also investigate the stability in utilization trendsfor low-risk consolidation. Using the insights from the workload analysis, two new consolidation methods are designed that achieve significant power savings, while containing the performanceriskofconsolidation.Wepresentanimplementationofthe methodologiesin a consolidationplanning tooland providea comprehensiveevaluationstudy oftheproposedmethodologies.