A novel algorithm for fast retrival of information from a multiprocessor server
Abdus Samad, Mohammad Qasim Rafiq, Omar Farooq · International Conference on Software Engineering · 2008
The popular resources in the internet are located in multiple servers that can be downloaded in parallel by a number of internet file downloading applications. In this paper an overview of a six nodes multiprocessor server, Linearly Extensible Cube (LEC), has been carried out to achieve both load balancing and downloading information efficiently. The dynamic scheduling algorithm to balance the load of multiprocessor is implemented. The database on the server is organized in such a way that a fast retrieval of information can be achieved. A new proposed algorithm is implemented on the server which uses store and forward like technique. A comparative simulation study has been carried out and the average time to download a file is computed. The simulation results show that the given multiprocessor architecture, when implemented as a server with the proposed algorithm reduces the resource download time.