期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2018
卷号：9
期号：11
DOI：10.14569/IJACSA.2018.091162
出版社：Science and Information Society (SAI)
摘要：Distributed applications have been developed using thread pool system (TPS) in order to improve system performance. The dynamic optimization and overload management of TPS are two crucial factors that affect overall performance of distributed thread pool (DTP). This paper presents a DTP, that is based on central management system, where a central manager forwards client’s requests in round robin fashion to available set of TPSs running in servers. The dynamic tuning of each TPS is done based on request rate on the TPS. The overload condition at each TPS is detected by the TPS itself, by throughput decline. The overload condition is resolved by reducing the size of thread pool to previous value, at which it was producing throughput parallel to the request rates. By reducing the size of thread pool on high request rates, the context switches and thread contention overheads are eliminated that enables system resources to be utilized effectively by available threads in the pool. The result of evaluation proved the validity of proposed system.
