XtremWeb: A Generic Global Computing System
CCGRID '01 Proceedings of the 1st International Symposium on Cluster Computing and the Grid
Entropia: architecture and performance of an enterprise desktop grid system
Journal of Parallel and Distributed Computing - Special issue on computational grids
Peer-to-Peer Computing: Technologies for Sharing and Collaborating on the Net
Peer-to-Peer Computing: Technologies for Sharing and Collaborating on the Net
Grid Computing: A Practical Guide to Technology and Applications
Grid Computing: A Practical Guide to Technology and Applications
BOINC: A System for Public-Resource Computing and Storage
GRID '04 Proceedings of the 5th IEEE/ACM International Workshop on Grid Computing
Sharing Checkpoints to Improve Turnaround Time in Desktop Grid
AINA '06 Proceedings of the 20th International Conference on Advanced Information Networking and Applications - Volume 01
Hi-index | 0.00 |
An important issue in the PC grid computing environment that is characterized by volatility and heterogeneity is the minimization of execution time for all tasks. This paper proposes a scheduling mechanism to reduce such execution time by means of both checkpoint sharing and task duplication under a peer-to-peer (P2P) architecture. In the mechanism, the checkpoint executed by an individual peer (i.e. , a desktop PC) is used as an intermediate result and executed in other peers via its duplication and transmission. As a result, as the checkpoint is close to a final result, the reduction of execution time for each task becomes higher. Ultimately, turnaround time can be reduced. Moreover, an analytical model with an embedded Markov chain is presented to evaluate the transmission cost and execution time of our scheduling mechanism. The performance of our scheduling mechanism is also compared with that of the existing mechanism operating on client-server architecture. The analytical results show that our scheduling mechanism is superior to the existing mechanism with respect to the reduction of execution time.