Design of optimal distributed file systems

作者: Uwe M. Borghoff

DOI: 10.1145/142854.142861

关键词:

摘要: In this paper, the problem of determining an optimal location strategy for individual program execution is considered. addition, we propose a heuristic approach dynamic file allocation problem. order to reduce complexity optimization problems, cluster-based used.To access data files distributed system, user initiates execution. Based on current and as well knowledge about characteristics programs, first calculates cluster each The objective minimization intercluster traffic Within cluster, simple load-balancing used determine corresponding executing node.A second looks allocations where global minimized subject following constraints: minimal number copies, availability, storage capacity.Experimental results showing efficiency proposed algorithms are examined, implications model design very large systems discussed.

参考文章(55)
Jacky Akoka, Design of Optimal Distributed Database Systems. DDB. pp. 229- 246 ,(1980)
Darrell Long, Jehan-François Pâris, None, Block-Level Consistency of Replicated Files. international conference on distributed computing systems. pp. 146- 153 ,(1987)
James F. Kurose, Rahul Simha, Second Derivative Algorithms for Optimal Resource Allocation in Distributed Computer Systems. international conference on distributed computing systems. pp. 56- 63 ,(1987)
James F. Kurose, Rahul Simha, A Microeconomic Approach to Optimal File Allocation. international conference on distributed computing systems. pp. 28- 35 ,(1986)
Anna Hác, Xiaowei Jin, Dynamic Load Balancing in a Distributed System Using a Decentralized Algorithm. international conference on distributed computing systems. pp. 170- 177 ,(1987)
Sushil Jajodia, David Mutchler, Enhancements to the Voting Algorithm very large data bases. pp. 399- 406 ,(1987)
Darrell Don Earl Long, Jehan-Francois Paris, The management of replication in a distributed system University of California, San Diego. ,(1988)
Uwe M. Borghoff, Voting and relocation strategies preserving consistency among replicated files international conference on database theory. pp. 318- 332 ,(1990) , 10.1007/3-540-53507-1_86