Optimizing Live Migration of Virtual Machines with Context Based Prediction Algorithm

DOI

10.2991/ccis-13.2013.102How to use a DOI?

Keywords

Virtual Machine; Live Migration; Context Based Prediction; Performance Evaluation

Abstract

With the increasing use of Virtual Machine (VM) in data center, live migration of virtual machine has become a powerful and essential instrument for resource management. Although the prevailing Pre-copy algorithm might perform well on the stage of lightweight, it cannot guarantee a desirable performance in the case of high dirty page rate or low network bandwidth. The resending problem results in striking performance degradation and waste of resource. Toward this issue, this paper presents a novel Context Based Prediction algorithm (CBP), which exploits PPM (Prediction by Partial Match) model to predict the dirty pages in the future iteration based on the historical statistics of dirty page bitmap. The transmissions of those frequently updated pages identified are postponed. Experiments demonstrate that CBP can achieve a satisfying balance between accuracy and overload, and shorten total migration time, downtime and total pages transfer

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Cui Yong
AU  - Lin Yusong
AU  - Guo Yi
AU  - Li Runzhi
AU  - Wang Zongmin
PY  - 2013/11
DA  - 2013/11
TI  - Optimizing Live Migration of Virtual Machines with Context Based Prediction Algorithm
BT  - Proceedings of the The 1st International Workshop on Cloud Computing and Information Security
PB  - Atlantis Press
SP  - 441
EP  - 444
SN  - 1951-6851
UR  - https://doi.org/10.2991/ccis-13.2013.102
DO  - 10.2991/ccis-13.2013.102
ID  - Yong2013/11
ER  -