A scheduling algorithm based on resource overcommitment in virtualization environments
Jibin Wang, Zhang Hu, Zhaogang Xu, Wenxiang He, Ying Guo · 2016
In large cloud data center where the virtualization technologies are widely used, a challenging issue is how to efficiently allocate and migrate virtual resources. In this paper, we propose a novel scheduling algorithm based on resource overcommitment, as called i-porter. The main goal of i-porter algorithm is to improve the utilizations of heterogeneous physical resources in virtualization environments. Compared to the existing solutions, i-porter has the following advantages: (1) it is a two levels of architecture that can meet the scheduling requirements, whether for virtual machine building or migration; (2) it makes the layouts of the virtual machines to be consistent and improves the cost-efficacy of the whole data center. Based on a prototype implementation of i-porter, our evaluation results show that i-porter algorithm performs excellent in resource scheduling and cost savings.