Fast In-kernel Traffic Sketching in eBPF

IF 2.2 4区 计算机科学 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS
S. Miano, Xiaoqi Chen, Ran Ben Basat, G. Antichi
{"title":"Fast In-kernel Traffic Sketching in eBPF","authors":"S. Miano, Xiaoqi Chen, Ran Ben Basat, G. Antichi","doi":"10.1145/3594255.3594256","DOIUrl":null,"url":null,"abstract":"The extended Berkeley Packet Filter (eBPF) is an infrastructure that allows to dynamically load and run micro-programs directly in the Linux kernel without recompiling it. In this work, we study how to develop high-performance network measurements in eBPF. We take sketches as case-study, given their ability to support a wide-range of tasks while providing low-memory footprint and accuracy guarantees. We implemented NitroSketch, the state-of-the-art sketch for user-space networking and show that best practices in user-space networking cannot be directly applied to eBPF, because of its different performance characteristics. By applying our lesson learned we improve its performance by 40% compared to a naive implementation.","PeriodicalId":50646,"journal":{"name":"ACM Sigcomm Computer Communication Review","volume":"42 1","pages":"3 - 13"},"PeriodicalIF":2.2000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Sigcomm Computer Communication Review","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3594255.3594256","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 3

Abstract

The extended Berkeley Packet Filter (eBPF) is an infrastructure that allows to dynamically load and run micro-programs directly in the Linux kernel without recompiling it. In this work, we study how to develop high-performance network measurements in eBPF. We take sketches as case-study, given their ability to support a wide-range of tasks while providing low-memory footprint and accuracy guarantees. We implemented NitroSketch, the state-of-the-art sketch for user-space networking and show that best practices in user-space networking cannot be directly applied to eBPF, because of its different performance characteristics. By applying our lesson learned we improve its performance by 40% compared to a naive implementation.
eBPF中的快速内核内流量绘制
扩展的Berkeley Packet Filter (eBPF)是一种基础结构,它允许直接在Linux内核中动态加载和运行微程序,而无需重新编译它。在这项工作中,我们研究了如何在eBPF中开发高性能的网络测量。我们将草图作为案例研究,因为它们能够支持广泛的任务,同时提供低内存占用和准确性保证。我们实现了用于用户空间网络的最先进草图NitroSketch,并表明用户空间网络中的最佳实践不能直接应用于eBPF,因为它具有不同的性能特征。通过应用我们的经验教训,我们将其性能提高了40%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
ACM Sigcomm Computer Communication Review
ACM Sigcomm Computer Communication Review 工程技术-计算机:信息系统
CiteScore
6.90
自引率
3.60%
发文量
20
审稿时长
4-8 weeks
期刊介绍: Computer Communication Review (CCR) is an online publication of the ACM Special Interest Group on Data Communication (SIGCOMM) and publishes articles on topics within the SIG''s field of interest. Technical papers accepted to CCR typically report on practical advances or the practical applications of theoretical advances. CCR serves as a forum for interesting and novel ideas at an early stage in their development. The focus is on timely dissemination of new ideas that may help trigger additional investigations. While the innovation and timeliness are the major criteria for its acceptance, technical robustness and readability will also be considered in the review process. We particularly encourage papers with early evaluation or feasibility studies.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信