Live Migration for Virtual Machine Based on Kalman Prediction of Dirty Pages
暂无分享,去创建一个
The live migration of virtual machine (VM) is an important technology of cloud computing. Down-time, total migration time and network traffic data are the key measures of performance. Through the analysis of dynamic memory state of a virtual machine migration process, we propose a dirty pages algorithm prediction based on pre-copy to avoid dirty pages re transmission. Experimental results show that, compared with the Xen virtual machine live migration method adopted, our method can at least reduce 15.1% of the total amount of data and 12.2% of the total migration time.
[1] Hai Jin,et al. Live virtual machine migration with adaptive, memory compression , 2009, 2009 IEEE International Conference on Cluster Computing and Workshops.
[2] Umesh Deshpande,et al. Post-copy live migration of virtual machines , 2009, OPSR.
[3] Andrew Warfield,et al. Live migration of virtual machines , 2005, NSDI.
[4] Karsten Schwan,et al. VirtualPower: coordinated power management in virtualized enterprise systems , 2007, SOSP.