Title :
Sensitivity evaluation of dynamic load sharing in distributed systems
Author :
Dandamudi, Sivarama P.
Author_Institution :
Centre for Parallel & Distributed Comput., Carleton Univ., Ottawa, Ont., Canada
Abstract :
Load sharing improves the performance of distributed systems by moving work from heavily loaded to lightly loaded nodes. The author compares the performance of two principal load sharing policies under different circumstances, providing a generalized description of their behavior that holds true regardless of the specific system and workload models, and parameter values
Keywords :
distributed processing; performance evaluation; resource allocation; distributed systems; dynamic load sharing; generalized description; lightly loaded nodes; load sharing policies; parameter values; sensitivity evaluation; workload models; Costs; Distributed computing; Fluctuations; Proposals; Virtual machining; Workstations; Yarn;
Journal_Title :
Concurrency, IEEE
DOI :
10.1109/4434.708257