Preemptable remote execution facilities for the V-system

作者: Marvin M. Theimer , Keith A. Lantz , David R. Cheriton

DOI: 10.1145/323627.323629

关键词:

摘要: A remote execution facility allows a user of workstation-based distributed system to offload programs onto idle workstations, thereby providing the with access computational resources beyond that provided by his personal workstation. In this paper, we describe design and performance in V system, as well several implementation issues interest. particular, focus on network transparency environment, preemption migration remotely executed programs, avoidance residual dependencies original host. We argue preemptable workstations be used "pool processors" without interfering use their owners significant overhead for normal programs. general, conclude cost is modest compared similar amount computation service dedicated "computation engines".

参考文章(17)
R. Novarese, R. Marcogliese, Module and Data Allocation Methods in Distributed Systems. international conference on distributed computing systems. pp. 50- 59 ,(1981)
Ayache, Courtiat, Diaz, REBUS, A Fault-Tolerant Distributed System for Industrial Real-Time Control IEEE Transactions on Computers. ,vol. 31, pp. 637- 647 ,(1982) , 10.1109/TC.1982.1676061
A. J. Herbert, The Cambridge Distributed Computing System Proceedings on Local Area Networks: An Advanced Course. pp. 282- 312 ,(1983)
T.C.K. Chou, J.A. Abraham, Load Balancing in Distributed Systems IEEE Transactions on Software Engineering. ,vol. 8, pp. 401- 412 ,(1982) , 10.1109/TSE.1982.235574
Michael L. Powell, Barton P. Miller, Process migration in DEMOS/MP symposium on operating systems principles. ,vol. 17, pp. 110- 119 ,(1983) , 10.1145/773379.806619
K. A. Lantz, W. I. Nowicki, Structured Graphics for Distributed Systems ACM Transactions on Graphics. ,vol. 3, pp. 23- 51 ,(1984) , 10.1145/357332.357334
Daniel H. Craft, Resource management in a decentralized system symposium on operating systems principles. ,vol. 17, pp. 11- 19 ,(1983) , 10.1145/773379.806611