Abstract | ||
---|---|---|
Random Stealing (RS) is a well-known dynamic load-balancing algorithm, used both in shared-memory and distributed-memory systems. However, for a large-scale cluster, the simple RS policy is no longer efficient because an idle node must randomly steal many times to obtain a task from another node. In this paper, we propose a novel dynamic load-balancing algorithm, Transitive Random Stealing (TRS), which can make any idle node obtain a task from another node with much fewer stealing times in a large-scale cluster. Analysing and testing show that TRS is a highly efficient dynamic load-balancing algorithm in a large-scale cluster. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1504/IJHPCN.2009.027460 | IJHPCN |
Keywords | Field | DocType |
simple rs policy,random stealing,testing show,transitive random stealing,efficient dynamic load-balancing algorithm,novel dynamic load-balancing algorithm,distributed-memory system,idle node,well-known dynamic load-balancing algorithm,large-scale cluster,probabilistic model,load distribution | Shared memory,Load balancing (computing),Dynamic load testing,Computer science,Idle,Parallel computing,Distributed memory,Statistical model,Dynamic load balancing,Distributed computing,Transitive relation | Journal |
Volume | Issue | Citations |
6 | 2 | 5 |
PageRank | References | Authors |
0.53 | 9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bao-yin Zhang | 1 | 28 | 5.21 |
Zeyao Mo | 2 | 73 | 19.48 |
Guangwen Yang | 3 | 599 | 92.40 |
Weimin Zheng | 4 | 1889 | 182.48 |