Title :
Designing a distributed queue
Author :
Johnson, Theodore
Author_Institution :
Dept. of Comput. & Inf. Sci., Florida Univ., Gainesville, FL, USA
Abstract :
A common paradigm for distributed computing is the producer-consumer model. One set of processes produce objects (data, resources, or tasks) that are consumed by another set of processes. We present a simple algorithm for implementing a distributed queue. This algorithm has several parameters that need to be tuned, such as the number of probes to find an object, the amount of buffering, and the connectivity between the producers and the consumers. We provide an analytical model that predicts performance and based on the analytical model we provide recommendations for setting the parameters. Our analytical model is validated by a comparison to simulation results
Keywords :
data structures; distributed processing; queueing theory; software performance evaluation; analytical model; distributed computing; distributed queue; performance; producer-consumer model; Analytical models; Buffer storage; Computational modeling; Distributed computing; Information science; Parallel programming; Predictive models; Probes; Scheduling algorithm; Stochastic processes;
Conference_Titel :
Parallel and Distributed Processing, 1995. Proceedings. Seventh IEEE Symposium on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-81867195-5
DOI :
10.1109/SPDP.1995.530699
