Computer Science – Distributed – Parallel – and Cluster Computing
Scientific paper
2006-05-15
In Proceedings of the 8th IEEE International Conference on Cluster Computing (Cluster 2006), IEEE Computer Society Press, Sept
Computer Science
Distributed, Parallel, and Cluster Computing
Scientific paper
The Service Level Agreement~(SLA) based grid superscheduling approach promotes coordinated resource sharing. Superscheduling is facilitated between administratively and topologically distributed grid sites by grid schedulers such as Resource brokers. In this work, we present a market-based SLA coordination mechanism. We based our SLA model on a well known \emph{contract net protocol}. The key advantages of our approach are that it allows:~(i) resource owners to have finer degree of control over the resource allocation that was previously not possible through traditional mechanism; and (ii) superschedulers to bid for SLA contracts in the contract net with focus on completing the job within the user specified deadline. In this work, we use simulation to show the effectiveness of our proposed approach.
Buyya Rajkumar
Harwood Aaron
Ranjan Rajiv
No associations
LandOfFree
SLA-Based Coordinated Superscheduling Scheme and Performance for Computational Grids does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with SLA-Based Coordinated Superscheduling Scheme and Performance for Computational Grids, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and SLA-Based Coordinated Superscheduling Scheme and Performance for Computational Grids will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-621328