Reliable job execution with process failure recovery in computational grid
by P. Latchoumy; P. Sheik Abdul Khader
International Journal of Information and Communication Technology (IJICT), Vol. 7, No. 6, 2015

Abstract: Grid computing provides a virtual framework that integrates heterogeneous resources and services distributed across multiple controlled domains. Dynamic grid environment makes the grid infrastructure unreliable, resulting in failure of executing jobs. The great challenge here is to provide the reliable job execution in the presence of resource failure. In this paper, we present a new model called reliable job execution with process failure recovery in computational grid. In this model, the reliability of sites is monitored and the historical data is used for predicting resource failures taken into account when dispatched user jobs to resources and it recovers the failed job after the process failure has occurred. If the process failure occurs due to CPU overloads or memory thrashing, the backup process starts to run from the recently saved checkpoint. This system also considers the availability of checkpoints by storing checkpoints in multiple backup checkpoint servers. The experimental results demonstrate that our proposed strategy provides the guaranteed service to the grid user within the specified deadline.

Online publication date: Wed, 30-Sep-2015

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 Information and Communication Technology (IJICT):
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