Starfish: Fault-Tolerant Dynamic MPI Programs on Clusters of Workstations |
| |
Authors: | Adnan Agbaria Roy Friedman |
| |
Institution: | (1) The Technion, Department of Computer Science, Haifa, 32000, Israel |
| |
Abstract: | This paper reports on the architecture and design of Starfish, an environment for executing dynamic (and static) MPI-2 programs on a cluster of workstations. Starfish is unique in being efficient, fault-tolerant, highly available, and dynamic as a system internally, and in supporting fault-tolerance and dynamicity for its application programs as well. Starfish achieves these goals by combining group communication technology with checkpoint/restart, and uses a novel architecture that is both flexible and portable and keeps group communication outside the critical data path, for maximum performance. |
| |
Keywords: | checkpoint/restart fault-tolerance distributed system high performance MPI |
本文献已被 SpringerLink 等数据库收录! |
|