Performance evaluation of bandwidth for virtual machine migration in cloud computing
by Aditya Bhardwaj; C. Rama Krishna
International Journal of Knowledge Engineering and Data Mining (IJKEDM), Vol. 5, No. 3, 2018

Abstract: The proliferation of virtualisation enables cloud computing industries, such as Amazon, IBM, Google, Microsoft, and Rackspace to increase their physical hardware utilisation by multi-tenant model. One important key characteristic of server virtualisation is virtual machine (VM) migration. With the popularity of cloud paradigm, the number of enterprise applications deployed over cloud-systems are increasing. This shift in cloud services has brought new challenges of frequently varying resource requirement by the VM migration operation. Inaccurate allocation of bandwidth may affect end-user experience and reduce the cloud service provider's profit, Therefore, in this work we setup QEMU-KVM cloud VM migration experimental testbed environment and run CPU, memory intensive cloud benchmarks on the migrated VM. From the experimental results, it is found that increase in bandwidth significantly lower the migration time and downtime up-to an extent, however, reserving maximum bandwidth does not help anymore for performance improvement of migration mechanism.

Online publication date: Fri, 14-Sep-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Knowledge Engineering and Data Mining (IJKEDM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com