CC* Data Storage: High-Capacity Active Archive to Enable Economical Data Access and Distribution for Illinois Researchers and the National Community

CC* 数据存储：大容量主动存档，为伊利诺伊州研究人员和国家社区提供经济的数据访问和分发

• 批准号: 2346737
• 负责人: John Maloney
• 金额: $ 50万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-04-01 至 2026-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2346737&HistoricalAwards=false
• 关键词: CC; Data; Storage; Capacity; Active

With continued development of high-resolution instruments, networked sensors, and the ability to deploy these tools in an ever-growing number of capacities, the need for researchers to store and share large datasets has never been more pressing. Additionally, the rise of new data processing techniques leveraging the power of machine learning and AI algorithms allow researchers to glean new insights from existing datasets than was initially thought possible when the data was first captured. Science domains from agriculture to physics and medical imaging to astronomy, require larger and larger data storage options that allow for durable storage with robust data sharing capabilities.Granite is a cutting-edge tape-based data subsystem that allows researchers to store and retrieve data both via traditional POSIX methods, such as via Globus, and newer, more flexible standards, such as S3. These interfaces connect researchers to Granite’s 19-frame SpectraLogic TFinity dual-robotic tape library with 20 LTO-9 tape drives, 36PB of raw tape capacity, and Versity’s ScoutFS/ScoutAM archive management tools. Connectivity to Granite is provided by redundant 100Gbps paths to the University of Illinois Urbana-Champaign’s Science DMZ, Internet2, the Energy Sciences Network (ESnet), the Big Ten Academic Alliance’s OmniPoP, and the Metropolitan Research & Education Network (MREN). Available to Illinois researchers via the Illinois Data Bank and other Illinois allocation processes, and to the national research community via integration with the NSF Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (ACCESS) capability, Granite serves a large segment of researchers across the United States.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.

随着高分辨率仪器、网络传感器的不断发展，以及以越来越多的能力部署这些工具的能力，研究人员存储和共享大型数据集的需求从未如此紧迫。此外，利用机器学习和人工智能算法的新数据处理技术的兴起，使研究人员能够从现有数据集中收集新的见解，而不是最初捕获数据时最初认为可能的见解。从农业到物理学，从医学成像到天文学，科学领域都需要越来越大的数据存储选项，以实现持久的存储和强大的数据共享功能。Granite是一个先进的基于磁带的数据子系统，允许研究人员通过传统的POSIX方法（如通过Globus）和更新的更灵活的标准（如S3）存储和检索数据。这些接口将研究人员连接到Granite的19帧SpectraLogic TFinity双机器人磁带库，该磁带库具有20个LTO-9磁带驱动器、36 PB的原始磁带容量和Versity的ScoutFS/ScoutAM存档管理工具。与花岗岩的连接是通过冗余的100 Gbps路径提供的，这些路径连接到伊利诺伊大学厄巴纳-香槟分校的科学DMZ、Internet 2、能源科学网络（ESnet）、十大学术联盟的OmniPoP和大都会研究教育网络（MREN）。通过伊利诺伊州数据库和其他伊利诺伊州分配流程向伊利诺伊州研究人员提供，并通过与NSF高级网络基础设施协调生态系统：服务支持（ACCESS）功能集成向国家研究社区&提供，花岗岩服务于美国各地的研究人员的很大一部分。这个奖项反映了NSF的法定使命，并已被认为是值得通过评估使用基金会的知识优点和更广泛的影响审查标准。