CSR--AES: Employing Peer-to-Peer Services for Robust Grid Computing

点击翻译按钮获取中文摘要

The project will design and build a massively scalable infrastructure for executing grid applications on a widely distributed set of resources. Such infrastructure will be decentralized, robust, highly available, and secure, while efficiently mapping applications to available resources throughout the system. This proposal addresses the crucial problem of job placement in a completely distributed and decentralized manner. The proposed methods include a distributed algorithm for submitting jobs and efficiently matching them to available resources, and P2P techniques for both load-balance and for resilience; preliminary analysis indicated the proposed scheme scale is seamlessly with system size, and is robust against component failures and peer departures/joins. The project will implement, and validate the system developed using a set of problems in computational astronomy. The work proposed here will make robust, reliable, large-scale computing resources available to users from a broad range of scientific disciplines, allowing users to form ad-hoc resource-sharing communities. Such a system will enable scientists to seamlessly contribute resources to the community and to utilize these resources as needed. All the software developed as part of this proposal will be made publicly available and will help other researchers as well as practitioners to better evaluate the software produced and to build on it.