Abstract

LHD short pulse experiments are executed every three minutes. After the end of the discharge, the scientists must collect, analyze, visualize the last acquired data of the discharge, and prepare for the next discharge. From the beginning, the computer environment of the LHD (Large Helical Device) experiment has been built as a network distributed system, and various computers have been used for data acquisition or physical analysis. When one program is finished on one computer, that computer must send the results in order to the other computers to run programs. Smooth communication is required in order to finish all the tasks before the next discharge. To exchange the information among the applications running on the different computers, the authors have tried various methods, such as a commercial software to share the memory over the network, simple network file sharing method, IP multicast, web interfaces, and others. The purpose of this paper is to share our experiences of trial and error to build the network distributed systems for the consecutive plasma discharge experiments.

Full Text
Published version (Free)

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 call