EASE: Energy Efficiency and Proportionality Aware Virtual Machine Scheduling

• Congfeng Jiang Hangzhou Dianzi University
• Yumei Wang Hangzhou Dianzi University
• Dongyang Ou Hangzhou Dianzi University
• Yeliang Qiu Hangzhou Dianzi University
• Youhuizi Li Hangzhou Dianzi University
• Jian Wan Zhejiang University of Science and Technology Hangzhou
• Bing Luo Wayne State University
• Weisong Shi Wayne State University
• Christophe Cerin Sorbonne Paris Cite’ LIPN/CNRS UMR, University of Paris 13

Resumo

Servers have different energy efficiency and energy proportionality (EP) due to their hardware configuration (i.e., CPU generation and memory installation) and workload. However, current virtual machine (VM) scheduling in virtualized environments will saturate servers without considering their energy efficiency and EP differences. This article will discuss EASE, the energy efficiency and proportionality aware VM scheduling approach. EASE first executes customized computing intensive, memory intensive, and hybrid benchmarks to calculate a server's energy efficiency and EP. Then it schedules VMs to servers to keep them working at their peak energy efficiency point (or optimal working range). This step improves the overall energy efficiency of the cluster and the data center. For performance guarantee, EASE migrates VMs from servers under highly contending conditions. The experimental results on real clusters show that power consumption can be saved 37.07% ~ 49.98% in the homogeneous cluster. The average completion time of the computing intensive VMs increases only 0.31 % ~ 8.49%. In the heterogeneous nodes, the power consumption of the computing intensive VMs can be reduced by 44.22 %. The job completion time can be saved by 53.80%.

Palavras-chave: Servers, Energy efficiency, Power demand, Virtual machining, Job shop scheduling, Data centers, Memory management, energy efficiency, energy proportionality, virtual machine, data center, scheduling