Abstract
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.
Highlights
The ever-growing expansion of Internet and World Wide Web demands scalable services that must be performance efficient and highly available
This work is based on our previous work [14], in which, we have presented a distributed framework of thread pool system (TPS) called distributed frequency based thread pool (DFBTP), where each server node has its own TPS, that is tuned on the basis of request arrival rate, and the load on each node is balanced by a round robin strategy in order to fairly distribute the load among available TPSs
First machine has a client tier of toolkit, second machine is used as a main server running central manager (CM) and third machine is used as a slave running a TPS
Summary
The ever-growing expansion of Internet and World Wide Web demands scalable services that must be performance efficient and highly available. OSN sites such as LinkedIn, Flickr, Myspace, Twitter and Facebook provide facilities to over half a billion users at the same time [1]. Number of third-party applications run by the Facebook are over 81,000 [1]. There is a profound impact of these third-party applications on the application server’s scalability and performance results in additional traffic. In order to deal with these complexities, internet services are provided by distributed application servers [4], that are responsible of providing run time services to applications, where these applications service demands of many concurrent users
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
