Research on Virtual Device Management in Real-time Environment

DOI

10.2991/anit-17.2018.16How to use a DOI?

Keywords

Virtualization, scheduling algorithm, mixed load, Xen

Abstract

In this paper, we present improved methods of credit scheduling algorithm of Xen. By using gray-box knowledge reasoning technology, we are able to identify the IO task in the internal workload of each virtual machine. By using this information of the internal workload, we proposed a Boosting mechanism based on the selection. Selectively raise the priority of the virtual processor to give priority to the corresponding field of the I/O Tasks improve the response speed, and reduce the response time to achieve real-time purposes. In addition, we propose four complementary mechanisms for the shortcomings of the proposed BOOST scheduling algorithm based on the selection. The four complementary mechanisms are the cancellation BOOST priority mechanism, reducing Credit precise mechanism, setting Rate value mechanisms and UNDER queue mechanisms. These four mechanisms can effectively fill the insufficient of BOOST scheduling algorithm based selection, and improve the stability of the algorithm.

Copyright

© 2018, 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  - Wenjia Gong
AU  - Yongchao Tao
AU  - Wencheng Xiang
AU  - Xianghu Wu
PY  - 2017/12
DA  - 2017/12
TI  - Research on Virtual Device Management in Real-time Environment
BT  - Proceedings of the 2017 International Seminar on Artificial Intelligence, Networking and Information Technology (ANIT 2017)
PB  - Atlantis Press
SP  - 84
EP  - 89
SN  - 1951-6851
UR  - https://doi.org/10.2991/anit-17.2018.16
DO  - 10.2991/anit-17.2018.16
ID  - Gong2017/12
ER  -