Collaborative Research: Chameleon: A Large-Scale, Reconfigurable Experimental Environment for Cloud Research

协作研究：Chameleon：用于云研究的大规模、可重构实验环境

• 批准号: 1743358
• 负责人: Katarzyna Keahey
• 金额: $ 537.97万
• 依托单位: University of Chicago
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1743358&HistoricalAwards=false
• 关键词: Collaborative; Research; Chameleon; Large; Scale

One of two NSFCloud mid-scale experimental computing research infrastructures, Chameleon is a deeply reconfigurable cloud computing testbed supporting large-scale Computer Science experimentation. Located at the University of Chicago and the Texas Advanced Computing Center, it is composed of over 600 compute nodes and a total of 5 petabytes of storage supporting data-intensive science. Since its public availability in July 2015, Chameleon has attracted a community of over 1,300 users working on over 200 education and research projects.In Phase 2 of the NSFCloud program, this project will expand Chameleon capabilities and capacity, and will fulfill its mission of serving as a testbed that is used extensively by the research community by:1) broadening the set of supported experiments through the addition of new hardware and software supporting high bandwidth and Software Defined Networking (SDN)2) providing operational sustainability by streamlining operations, packaging the testbed as open source software that can be leveraged by others, and developing a process for adding resources to the testbed3) provide support for managing, understanding, comparing and reproducing Computer Science experiments, and4) focusing effort on building an engaged community around the testbed via both traditional outreach including targeted training and education efforts, and direct personalized outreach to experimenters.

Chameleon 是两个 NSFCloud 中型实验计算研究基础设施之一，是一个可深度重构的云计算测试平台，支持大规模计算机科学实验。它位于芝加哥大学和德克萨斯州高级计算中心，由 600 多个计算节点和总共 5 PB 的存储组成，支持数据密集型科学。自 2015 年 7 月公开发布以来，Chameleon 已吸引了超过 1,300 名用户参与 200 多个教育和研究项目。在 NSFCloud 计划的第二阶段，该项目将扩展 Chameleon 的功能和容量，并将履行其服务使命作为研究界广泛使用的测试平台：1) 通过添加支持高带宽和软件定义网络 (SDN) 的新硬件和软件来扩大支持的实验集2) 提供运营可持续性通过简化操作，将测试台打包为可供其他人使用的开源软件，以及开发向测试台添加资源的流程3）为管理、理解、比较和重现计算机科学实验提供支持，以及4）集中精力构建一个通过传统的外展活动（包括有针对性的培训和教育工作）以及对实验者的直接个性化外展活动，吸引测试平台周围的社区参与。

项目成果

Managing Allocatable Resources

管理可分配资源

• 发表时间: 2019-01
• 期刊: IEEE ... International Conference on Cloud Computing
• 作者: Keahey, Kate;Riteau, Pierre;Anderson, Jason;Zhen, Zhuo
• 通讯作者: Zhen, Zhuo

Overcast: Running Controlled Experiments Spanning Research and Commercial Clouds

阴天：运行跨越研究和商业云的受控实验

• 发表时间: 2021-01
• 期刊: Proceedings of the IEEE Conference Computer and Networking Experimental Research using Testbeds (CNERT 2021
• 作者: Ruth, P.;Keahey, K.;Cevik, M.;Zhen, Z.;Wang, C.;Anderson, J.
• 通讯作者: Anderson, J.

Operational Lessons from Chameleon

变色龙的操作经验

• 发表时间: 2019-01
• 期刊: Proceedings of the Humanware Advancing Research in the Cloud
• 作者: Keahey, Kate;Anderson, Jason;Ruth, Paul;Colleran, Jacob;Hammock, Cody;Stubbs, Joe;Zhen, Zhuo
• 通讯作者: Zhen, Zhuo

Wide-area Software Defined Networking Experiments using Chameleon

使用 Chameleon 进行广域软件定义网络实验

• 发表时间: 2019-01
• 期刊: IEEE Conference on Computer Communications workshops
• 作者: Ruth, Paul;Cevik, Mert;Keahey, Kate;Riteau, Pierre
• 通讯作者: Riteau, Pierre

Lessons Learned from the Chameleon Testbed

从 Chameleon 测试台吸取的经验教训

• 发表时间: 2020-07
• 期刊: Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC '20
• 作者: Keahey, K.;Anderson, J.;Zhen, Z;Riteau, P.;Ruth, P.;Stanzione, D.;Cevik, M.;Colleran, J.;Gunawi, H.S.;Hammock, C.;et al
• 通讯作者: et al