Collaborative Research: PPoSS: Planning: Making Smart Use of SmartNICs

协作研究：PPoSS：规划：巧妙利用 SmartNIC

• 批准号: 2028832
• 负责人: Aurojit Panda
• 金额: $ 8万
• 依托单位: New York University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2028832&HistoricalAwards=false
• 关键词: Collaborative; Research; PPoSS; Planning; Making

Computing paradigms occasionally undergo rather dramatic shifts as underlying technologies change, significantly modifying the dominant use cases. Some of these revolutions are seen far in advance and are heralded by great fanfare, with the hype long preceding the actual payoffs. Others are more opportunistic in nature, leveraging a technology initially developed for another purpose, and the adoption of this technology starts altering practice without much notice from the broader community. Computing is now on the verge of such a “quiet revolution” having to do with inserting computation on the devices that connect computers to the network. This trend towards what are called SmartNICs (for computationally enhanced network interface cards) shows great promise in both making applications faster and in keeping data more secure. This project will focus on how to best leverage SmartNICs in order to improve application performance and security.SmartNICs were originally designed to offload packet-processing from the host CPU, which processing is necessary in certain settings to perform encryption and other compute-intensive tasks on the data path. SmartNICs combine this packet-processing power with three other characteristics: (i) isolation from the host CPU, (ii) direct access to memory, and (iii) general programmability. It turns out that this combination gives SmartNICs the potential to play a powerful and unique role in the overall computational ecosystem. In particular, by sitting on the boundary between the network and hosts, they can change the interfaces being exposed to both, allowing SmartNICs to substantially improve application performance while also providing greater security and privacy. However, realizing these gains requires making progress on three separate issues. First, the hardware design of SmartNICs must combine several different units (a specialized packet-handling unit, an remote direct memory access unit, and a general computation unit), and provide fast interconnections between them and with the host memory. The design space is vast, and there is little agreement on what designs represent the best trade-offs. Second, these SmartNICs must offer applications a set of primitives that can improve their performance and security. These primitives must be chosen wisely to be feasible for SmartNICs to support while being easy for applications to leverage for better performance and security. Third, verification tools are needed to ensure that the programs on the SmartNIC are correctly executed and that the overall system -- running on multiple hosts and their SmartNICs -- is correct. This will require extensions to current verification techniques.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.

随着底层技术的变化，计算范式偶尔会经历相当戏剧性的变化，显著地修改了主要用例。其中一些革命被提前看到，并被大张旗鼓地宣传，在实际回报之前很久就被大肆宣传。另一些人则在本质上更投机取巧，利用最初为其他目的开发的技术，而采用这种技术开始改变实践，而没有引起更广泛的社区的太多注意。计算现在正处于这样一场“安静的革命”的边缘，它与将计算插入连接计算机到网络的设备有关。这种被称为smartnic（用于计算增强的网络接口卡）的趋势在使应用程序更快和保持数据更安全方面显示出巨大的希望。该项目将重点关注如何最好地利用smartnic，以提高应用程序的性能和安全性。smartnic最初的设计是为了从主机CPU中卸载数据包处理，在某些设置下，在数据路径上执行加密和其他计算密集型任务是必要的。smartnic将这种数据包处理能力与其他三个特性相结合：(i)与主机CPU隔离，（ii）直接访问内存，以及（iii）一般可编程性。事实证明，这种组合使smartnic有潜力在整个计算生态系统中发挥强大而独特的作用。特别是，通过位于网络和主机之间的边界，它们可以改变暴露给两者的接口，从而使smartnic能够大幅提高应用程序性能，同时还提供更高的安全性和隐私性。然而，实现这些成果需要在三个不同的问题上取得进展。首先，smartnic的硬件设计必须将几个不同的单元（专门的数据包处理单元、远程直接内存访问单元和通用计算单元）组合在一起，并提供它们之间以及与主机内存之间的快速互连。设计空间是巨大的，对于什么样的设计代表了最好的折衷，人们几乎没有达成一致。其次，这些smartnic必须为应用程序提供一组可以提高其性能和安全性的原语。必须明智地选择这些原语，以使smartnic能够支持这些原语，同时使应用程序能够轻松地利用这些原语来获得更好的性能和安全性。第三，需要使用校验工具来确保SmartNIC上的程序正确执行，确保整个系统（运行在多个主机及其SmartNIC上）是正确的。这将需要扩展当前的验证技术。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值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

Remote Memory Calls

• DOI: 10.1145/3422604.3425923
• 发表时间: 2020-11
• 期刊: Proceedings of the 19th ACM Workshop on Hot Topics in Networks
• 作者: Emmanuel Amaro;Zhihong Luo;Amy Ousterhout;A. Krishnamurthy;Aurojit Panda;Sylvia Ratnasamy;S. Shenker

Isolation Mechanisms for High-Speed Packet-Processing Pipelines

• 发表时间: 2021-01
• 作者: Tao Wang;Xiangrui Yang;Gianni Antichi;Anirudh Sivaraman;Aurojit Panda

Bertha: Tunneling through the Network API

• DOI: 10.1145/3422604.3425927
• 发表时间: 2020-11
• 期刊: Proceedings of the 19th ACM Workshop on Hot Topics in Networks
• 作者: Akshay Narayan;Aurojit Panda;Mohammad Alizadeh;H. Balakrishnan;A. Krishnamurthy;S. Shenker

We need kernel interposition over the network dataplane

• DOI: 10.1145/3458336.3465281
• 发表时间: 2021-06
• 期刊: Proceedings of the Workshop on Hot Topics in Operating Systems
• 作者: Hugo Sadok;Zhipeng Zhao;Valerie Choung;Nirav Atre;Daniel S. Berger;J. Hoe;Aurojit Panda;Justine Sherry