CAREER: Effective Grid Programming with EveryWare and G-commerce

随着网络性能的提高，高性能计算社区已经开始转向分布式系统来满足他们的性能需求。将并行计算的并发管理技术与可扩展和自适应分布式系统设计相结合的研究产生了一种新的软件体系结构，称为“计算网格”。它的主要宗旨是，用户程序应该能够从分布式资源池中获取计算“能力”，就像电器从电力设施中获取电力一样：无处不在、无缝且可靠。本项目将研究一种新的方法来构建实现“计算网格”计算模型的软件系统，以及如何在此调查的基础上培养新的课程方向。作为这项工作的载体，两个研究重点将以EveryWare和G-commerce的形式结合起来，为网格定义一种新的编程方法。EveryWare是一个软件工具包，用于构建健壮、高性能的分布式应用程序，这些应用程序可以使用现有的计算网格中间件作为构建块。EveryWare程序被构建为一组应用程序可定制服务，这些服务使用EveryWare工具包作为自适应服务器框架，同时利用现有网格系统提供的功能。G-commerce是一个计算经济系统，它允许应用程序从计算供应商那里购买资源。电子商务的一个关键特征是它是一个可以证明实现经济均衡和市场稳定的宏观经济系统。通过结合这两者，我们将定义一种新的强大的网格应用程序编程方法。为此，我们将：扩展和实现EveryWare软件工具包；研究和开发将构成基于G-commerce的资源分配策略基础的经济公式，开发用于实施资源经济的计算交换和用于经验G-commerce资源调度研究的基础设施。在“实时”网格设置中使用重要的网格应用程序验证我们的结果。本课题的研究方法是分析与实验相结合的。本文将从理论和仿真两方面探讨资源配置的稳定性和均衡性问题。然后使用计算交换实现有希望的经济公式，并在网格应用的每个ware实现中测试它们的有效性。同时，EveryWare将得到增强，使应用程序程序员和调度器在做出资源分配决策时能够考虑计算价格。EveryWare和G-commerce也将成为课程发展新方向的基础。将设计一个课程序列，结合分布式计算技术，负载条件的统计分析，以及文献中的经济建模方法，并使用计算网格进行实际实施。由此产生的多学科课程将使学生能够轻松地比较和组合不同的策略，以便进行定量评估，这将是每个序列的主要焦点。还将组织来自不同大学的学生参加实习。每个实习将侧重于使用不同计算网格基础设施的选定应用程序的实现。学生将比较不同的技术，并使用EveryWare工具包和g -commerce将最有效的技术结合起来。

As network performance has increased, the high-performance computing community has begun toturn to distributed systems to meet their performance needs. Research that combines the concurrencymanagement techniques from parallel computing with scalable and adaptive distributed systems design has resulted in a new software architecture known as the "Computational Grid". Its main tenet is that user programs should be able to draw computational "power" from a distributed resource pool the wayelectrical appliances draw electricity from a power utility: ubiquitously, seamlessly and reliably. Thisproject will investigate a novel approach to building software systems that implement the" ComputationalGrid" model of computing and how to foster new curricular directions based on this investigation.As vehicles for this proposed work, two research thrusts will be combined in the form of EveryWare and G-commerce to define a new programming methodology for the Grid. EveryWare is a software toolkit for building robust, high-performance distributed applications that can use existing Computational Gridmiddleware as building blocks. An EveryWare program is structured as a set of application customizableservices that use the EveryWare toolkit as an adaptive server framewirk while leveraging the functionalityprovided by existing Grid systems. G-commerce is a computational economic system that allows applications to purchase resources from computational suppliers. A key feature of G-commerce is that it is a macro-economic system which provably achieves economic equilibrium and market stability. By combining these two we will define a new and powerful approach to programming Grid applications.To do so we will:.extend and implement the EveryWare software toolkit,.study and develop economic formulations that will form the basis of G-commercebased resource allocation strategies,.develop a computational exchange for implementing resource economies aninfrastructure for empirical G-commerce resource scheduling studies and,.verify our results using non-trivial Grid applications in "live" Grid settings.The research approach of this project is both analytical and experimental.It will approach the problem of ensuring resource allocation stability andequilibrium theoretically and using simulation. Then implement promisingeconomic formulations using the computational exchange, and test theirvalidity with EveryWare implimentations of Grid applications. At the sametime, EveryWare will be enhanced so that it enables the aplication programmersand schedulers to consider computational price when making resource allocationdecisions.EveryWare and G-commerce will also serve as the basis for new directions incurriculum development. A course sequence will be designed that combinesdistributed computing techniques, statistical analysis of load conditions, andeconomic modeling methods from the literature with practical implementationusing Computational Grids. The resulting multi-disciplinary course will allowstudents to compare and combine different strategies easily for the purpose ofmaking quantitative evaluations, which will be a primary focus of each sequence.Practica will also be organized in which students from different Universitieswill be invited to participate. Each practicum will focus on the implementationof a chosen application using different Computational Grid infrastructures.Students will compare different techniques and use the EveryWare toolkit andG-commerce to combine those that are the most effective.