Efficient in live VM migration using working set prediction

Live migration is a key feature of system virtualization technologies. VM live migration basically consists of transferring its memory pages from a source server to a destination server. The amount of transferred memory pages affected the downtime and application performance of virtual machines. In pre-copy based live migration, virtual machine's service downtime is expected to be minimal but total migration time is prolonged by iterative copy operations and the significant amount of transferred data during the whole migration process. In this framework, a working set prediction algorithm is proposed as a preprocessing step. The proposed working set prediction algorithm which based on Least Recently Used (LRU) policy consists of working set list that collects the most recent used memory pages and inactive list that collects the least recent used memory pages. In iterative copy operations of the proposed framework, it transfers only inactive list and in stop and copy operation, it transfers working set list and CPU state.

Autorentext

Dr. Ei Phyu Zaw has obtained her PhD degree in Information Technology in 2012. Since then she has worked in different local and international projects in the field of Virtualization and Cloud Computing and has been serving as not only a teacher but also a supervisor for Master and PhD candidates in University of Computer Studies, Yangon.