Server workload analysis for power minimization using consolidation
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.