Universal Protocol And Inferface Based On Performance Management Of Grid

Along with the huge improvement and rapid progress of computer performance and network communicating technology, the development of application demands toward high- performance, large-scale, diversity and multi-function needs to connect the various high-performance computing resources, storage, data and other specific resources, which are geographically distributed and heterogeneous, via high speed network to establish collaborate high-performance computing and solve huge application problems cooperatively, hence the name wide-area high-performance meta computing technology, Grid Computing Technology as well. In the Grid Computing mode, the wide-area distinctions among hardwares, operation systems, organizations and regions are masked by Grid infrastructure, hence A"Virtual Super Computer"composed of all kinds of resources, is shared and managed transparently and efficiently by different users and organizations.To standardize Universal Protocol and Interface based on Performance Management in Grid environment, is a urgently solved question in Grid Computing. Resources and application programs are diverse among different administrative domain at various locations, which belong to different organizations and also different in deploy and security strategies in Grid Computing environment,. Most of them are inter-connected via the Internet, distributing widely on the geography with the huge types and quantities. To the development of the Grid Computing, a very important work is to build up a universal standard criterion in Grid Service, to inosculate nicely with Grid Computing and Web Service.This paper is a part of project"Realtime monitoring and predicting execution performance of Grid application"which is funded by National Natural Science Foundation. Include the following main work: Put forward a realtime monitormethod of the resources signal, establish a resources forecast model; Put forward a realtime measure and forecast method for the application of Grid to performance time, build up the application forecast model; Obtain the usage of resources, the circumstance of the application movement etc, Provide the universal protocol and interface standard of monitoring and managing for the resources and applications. So this paper...