Predicting the Performance of Parallel Computing Models Using Queuing System

Abstract

Computing models provide the parallel and distributed algorithms for cloud. The ability to estimate the performance of parallel computing models for efficient resource scheduling is critical. Current techniques for predicting the performance are mostly based on analyzing and simulating. The behavior of parallel computing model directly leads to the diversity of mathematical model. Without a general prediction model, it is very hard to compare fairly different parallel computing models in several critical aspects, including computing capacity, resource configuration, scalability, fault tolerance and so on. In this paper, we design a mathematical model for predicting the performance by using queuing system. We make various computing models as a service system for shielding the diversity. The performance can be accurately estimated with the job waiting time and the job performing time. The heterogeneity of computing nodes may also be considered.