FutureGrid: An Experimental, High-Performance Grid Test-bed

该项目提供了一种能力，使研究人员能够解决与网格和云的使用和安全相关的计算机科学中的复杂研究挑战。这些主题包括从身份验证、授权、调度、虚拟化、中间件设计、接口设计和网络安全，到为天文学、化学、生物学、工程、大气科学和流行病学研究人员优化网格和云计算方案。项目团队将向研究社区提供一个重要的新型实验计算网格和云测试平台，名为FutureGrid，同时为第三方研究人员在FutureGrid上进行实验提供用户支持。研究人员只要提交实验计划，就可以进行实验。然后通过一个复杂的工作流引擎执行，保留了允许再现性所需的来源和状态信息。试验台包括一组地理上分布的异构计算系统，一个数据管理系统，它将容纳元数据和一个不断增长的软件映像库，以及一个允许隔离、安全实验的专用网络。测试平台将支持基于虚拟机的环境，以及用于最小化开销和最大化性能的实验的本机操作系统。项目合作伙伴将集成现有的开源软件包，以创建一个易于使用的软件环境，支持网格和云计算实验的实例化、执行和记录。该项目的目标之一是理解云计算方法的行为和效用。研究人员将能够通过要求在虚拟和裸机系统上进行相关实验来测量云技术的开销。FutureGrid将使美国科学家能够开发和测试并行、网格和云计算的新方法，并与该领域的国际努力进行比较和合作。FutureGrid项目将提供一个容纳批处理、网格和云计算的实验平台，使研究人员能够解决与优化、集成和调度不同服务模型相关的一系列研究问题。FutureGrid还为中间件开发提供了一个测试平台，由于它的私有网络，中间件研究人员可以在不同的网络条件下进行控制实验，并测试中间件的方法，包括与网络控制层的直接交互。该项目的另一个组成部分是开发适用于网格计算的基准，包括来自天文学、生物信息学、地震学和物理学应用的基于工作流程的基准。FutureGrid将成为NSF TeraGrid高性能网络基础设施的一部分。它将增加TeraGrid的能力，以支持需要访问较低级别的网格软件堆栈、网络软件堆栈以及虚拟化和工作流编排工具的创新计算机科学研究。预计将于2011年10月1日完全整合到TeraGrid中。教育和更广泛的外展活动包括传播关于使用FutureGrid的课程材料、为特定课程模块配置的预先包装的FutureGrid虚拟机，以及基于虚拟设备网络和社会网络技术的教育模块，这些技术将侧重于网络、并行计算、虚拟化和分布式计算方面的教育。该项目将在计算资源较少的学术机构中推进分布式计算的教育和培训。它将通过开发教学资源来实现这一目标，这些资源包括为学生提供沙盒虚拟集群的预配置环境。这些可以用于并行、云和网格计算的教学课程。这些资源也将为学术机构提供一个简单的机会来试验云技术，看看这种技术是否可以增强他们的校园资源。FutureGrid项目利用了由国家科学基金会和能源部资助的几个软件开发项目的成果。

This project provides a capability that makes it possible for researchers to tackle complex research challenges in computer science related to the use and security of grids and clouds. These include topics ranging from authentication, authorization, scheduling, virtualization, middleware design, interface design and cybersecurity, to the optimization of grid-enabled and cloud-enabled computational schemes for researchers in astronomy, chemistry, biology, engineering, atmospheric science and epidemiology. The project team will provide a significant new experimental computing grid and cloud test-bed, named FutureGrid, to the research community, together with user support for third-party researchers conducting experiments on FutureGrid. The test-bed will make it possible for researchers to conduct experiments by submitting an experiment ?plan? that is then executed via a sophisticated workflow engine, preserving the provenance and state information necessary to allow reproducibility. The test-bed includes a geographically distributed set of heterogeneous computing systems, a data management system that will hold both metadata and a growing library of software images, and a dedicated network allowing isolatable, secure experiments. The test-bed will support virtual machine-based environments, as well as native operating systems for experiments aimed at minimizing overhead and maximizing performance. The project partners will integrate existing open-source software packages to create an easy-to-use software environment that supports the instantiation, execution and recording of grid and cloud computing experiments. One of the goals of the project is to understand the behavior and utility of cloud computing approaches. Researchers will be able to measure the overhead of cloud technology by requesting linked experiments on both virtual and bare-metal systems. FutureGrid will enable US scientists to develop and test new approaches to parallel, grid and cloud computing, and compare and collaborate with international efforts in this area. The FutureGrid project will provide an experimental platform that accommodates batch, grid and cloud computing, allowing researchers to attack a range of research questions associated with optimizing, integrating and scheduling the different service models. The FutureGrid also provides a test-bed for middleware development and, because of its private network, allows middleware researchers to do controlled experiments under different network conditions and to test approaches to middleware that include direct interaction with the network control layer. Another component of the project is the development of benchmarks appropriate for grid computing, including workflow-based benchmarks derived from applications in astronomy, bioinformatics, seismology and physics.The FutureGrid will form part of NSF's TeraGrid high-performance cyberinfrastructure. It will increase the capability of the TeraGrid to support innovative computer science research requiring access to lower levels of the grid software stack, the networking software stack, and to virtualization and workflow orchestration tools. Full integration into the TeraGrid is anticipated by 1st October 2011. Education and broader outreach activities include the dissemination of curricular materials on the use of FutureGrid, pre-packaged FutureGrid virtual machines configured for particular course modules, and educational modules based on virtual appliance networks and social networking technologies that will focus on education in networking, parallel computing, virtualization and distributed computing. The project will advance education and training in distributed computing at academic institutions with less diverse computational resources. It will do this through the development of instructional resources that include preconfigured environments that provide students with sandboxed virtual clusters. These can be used for teaching courses in parallel, cloud, and grid computing. Such resources will also provide academic institutions with a simple opportunity to experiment with cloud technology to see if such technology can enhance their campus resources. The FutureGrid project leverages the fruits of several software development projects funded by the National Science Foundation and the Department of Energy.