CloudLab Phase III: Expanding the Frontiers of Cloud Computing Through World-Class Community Infrastructure

CloudLab 第三阶段：通过世界一流的社区基础设施拓展云计算的前沿

• 批准号: 2027208
• 负责人: Robert Ricci
• 金额: $ 1000万
• 依托单位: University of Utah
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2027208&HistoricalAwards=false
• 关键词: CloudLab; Phase; III; Expanding; Frontiers

Cloud technologies underpin many of the apps and computing services that we use every day, including social networking, online commerce, email, video conferencing, and many more. To be able to do research that drives forward the fundamental architecture of the cloud, scientists need an environment in which they can experiment with the primary building blocks of the cloud: compute power, storage, and networks. CloudLab provides an environment where researchers can build their own clouds, observing and changing how they operate all the way to the bottom layers of software.CloudLab is a large facility, consisting, as of the start of this award, of more than 1,800 servers hosted at the University of Utah, Clemson University, and the University of Wisconsin-Madison. These servers include cutting-edge compute (such as several different processor architectures, graphics processing units, and field programmable gate arrays), networking (OpenFlow, user-programmable switching), and storage (hard drives, solid state drives) technologies. This phase III award will support the expansion of this facility by several hundred servers to meet high demand. It will also add new technologies, such as Internet of Things devices, programmable network cards, and non-volatile random access memory, which will in turn support research on data-intensive computing and computing at the edge of the network.CloudLab is available to researchers who work on the fundamentals of cloud computing. These users do research in areas such as networking, security, and databases; in turn, this work has broad impact, as these are the fundamental technologies upon which we build things such as smart cities, telehealth, online education, and other socially important computer services. Because it is offered at no cost for research and education to academic users, it acts as a level playing field on which institutions large and small, and those with many resources and those with few, can conduct work on an equal footing.CloudLab can be found online at https://cloudlab.us/, which is the primary interface through which research users interact with the facility, making it accessible from anywhere. This award will support continued operation of the facility, including the aforementioned hardware expansion, development of new features, and user support.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

云技术支撑着我们每天使用的许多应用程序和计算服务，包括社交网络、在线商务、电子邮件、视频会议等等。为了能够进行推动云基础架构发展的研究，科学家需要一个可以试验云的主要构建模块的环境：计算能力、存储和网络。 CloudLab 提供了一个环境，研究人员可以在其中构建自己的云，观察并改变它们的运行方式，直至软件的底层。CloudLab 是一个大型设施，截至本奖项颁发之初，由 1,800 多台托管服务器组成犹他大学、克莱姆森大学和威斯康星大学麦迪逊分校。这些服务器包括尖端计算（例如多种不同的处理器架构、图形处理单元和现场可编程门阵列）、网络（OpenFlow、用户可编程交换）和存储（硬盘驱动器、固态驱动器）技术。第三阶段的合同将支持该设施扩展数百台服务器，以满足高需求。它还将增加物联网设备、可编程网卡和非易失性随机存取存储器等新技术，从而支持数据密集型计算和网络边缘计算的研究。CloudLab可用于研究云计算基础知识的研究人员。这些用户在网络、安全和数据库等领域进行研究；反过来，这项工作也具有广泛的影响，因为这些是我们构建智慧城市、远程医疗、在线教育和其他对社会重要的计算机服务等事物的基础技术。由于它免费向学术用户提供研究和教育，因此它充当了一个公平的竞争环境，大大小小的机构、资源丰富的机构和资源匮乏的机构都可以在平等的基础上开展工作。CloudLab 可以可以在 https://cloudlab.us/ 上在线找到，这是研究用户与该设施交互的主要界面，使其可以从任何地方访问。该奖项将支持该设施的持续运营，包括上述硬件扩展、新功能开发和用户支持。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Cultivating Altruism Around Computing Resources: Anticipation Work in a Scholarly Community

围绕计算资源培养利他主义：学术界的预期工作

• DOI: 10.1145/3610185
• 发表时间: 2023
• 期刊: Proceedings of the ACM on Human-Computer Interaction
• 作者: Cohoon, Johanna;Kabir, Kazi Sinthia;Motahar, Tamanna;Wiese, Jason
• 通讯作者: Wiese, Jason

Avoiding the Ordering Trap in Systems Performance Measurement

避免系统性能测量中的排序陷阱

• 发表时间: 2023
• 期刊: Proceedings of the USENIX Annual Technical Conference (ATC
• 作者: Dmitry Duplyakin;Nikhil Ramesh;Carina Imburgia;Hamza Fathallah Al Sheikh;Semil Jain;Prikshit Tekta;Aleksander Maricq;Gary Wong;Robert Ricci
• 通讯作者: Robert Ricci