Optimizing interactive performance for desktop-virtualization environment

Authors:
Xiaolin Wang;Binbin Zhang;Yingwei Luo
Affiliations:
Dept. of Computer Science and Technology, Peking University, Beijing, China, The Shenzhen Key Lab for Cloud Computing Technology and Applications, Peking University Shenzhen Graduate School, Guang ...;Dept. of Computer Science and Engineering, Yunnan University, Yunnan, China;Dept. of Computer Science and Technology, Peking University, Beijing, China, The Shenzhen Key Lab for Cloud Computing Technology and Applications, Peking University Shenzhen Graduate School, Guang ...
Venue:
ICPCA/SWS'12 Proceedings of the 2012 international conference on Pervasive Computing and the Networked World
Year:
2012

Citing 5
Cited 0

Xen and the art of virtualization

SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
QEMU, a fast and portable dynamic translator

ATEC '05 Proceedings of the annual conference on USENIX Annual Technical Conference
Optimizing network virtualization in Xen

ATEC '06 Proceedings of the annual conference on USENIX '06 Annual Technical Conference
Scheduling I/O in virtual machine monitors

Proceedings of the fourth ACM SIGPLAN/SIGOPS international conference on Virtual execution environments
Software techniques to improve virtualized I/O performance on multi-core systems

Proceedings of the 4th ACM/IEEE Symposium on Architectures for Networking and Communications Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Full virtualization is vastly applied in desktop virtualization. Although hardware-assisted virtualization greatly improves the performance, the interactive performance is still a bottleneck for full virtualization. Interactive performance is mainly influenced by I/O devices. In one hand, I/O devices are slow device. In another hand, they are often shared by multiple virtual machines through simulation. Our study focuses on the interactive performance optimization, and can mainly be classified into three categories: (1) Targeting multi-core system, we investigate virtual machine deployment to ensure stable performance of the whole system and individual virtual machine. (2) Dynamically adjust the resource among virtual machines based on the individual machine's interactive behavior. (3) Optimize the I/O request scheduler in term of the virtualization implementation.