A Framework for Reproducible Data Plane Performance Modeling

Proceedings of the Symposium on Architectures for Networking and Communications Systems Pub Date : 2021-12-13 DOI:10.1145/3493425.3502756

D. Scholz, Hasanin Harkous, Sebastian Gallenmüller, Henning Stubbe, Max Helm, Benedikt Jaeger, N. Deric, Endri Goshi, Zikai Zhou, W. Kellerer, G. Carle

{"title":"A Framework for Reproducible Data Plane Performance Modeling","authors":"D. Scholz, Hasanin Harkous, Sebastian Gallenmüller, Henning Stubbe, Max Helm, Benedikt Jaeger, N. Deric, Endri Goshi, Zikai Zhou, W. Kellerer, G. Carle","doi":"10.1145/3493425.3502756","DOIUrl":null,"url":null,"abstract":"Languages for programming data planes like P4 sparked a plethora of new applications in the data plane. The dynamic, evolving environment makes it challenging to understand what performance can be expected when running a program in a specific data plane target. However, knowing this is crucial for network operators when upgrading their networks. We present a framework for the reproducible analysis and modeling of P4 program components. By defining and generating precise specifications of the experiments, we separate fully auto-generated components from testbed- or target-specific parts. Measurement results are used to derive performance models automatically. These can then be used to compare the measured with the theoretical performance, or to model the cost of entire paths through the data plane. In two case studies, we use our framework to discover and model selected behavior for a DPDK-based software target and for the NFP-4000 SmartNIC platform.","PeriodicalId":426581,"journal":{"name":"Proceedings of the Symposium on Architectures for Networking and Communications Systems","volume":"101 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Symposium on Architectures for Networking and Communications Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3493425.3502756","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Languages for programming data planes like P4 sparked a plethora of new applications in the data plane. The dynamic, evolving environment makes it challenging to understand what performance can be expected when running a program in a specific data plane target. However, knowing this is crucial for network operators when upgrading their networks. We present a framework for the reproducible analysis and modeling of P4 program components. By defining and generating precise specifications of the experiments, we separate fully auto-generated components from testbed- or target-specific parts. Measurement results are used to derive performance models automatically. These can then be used to compare the measured with the theoretical performance, or to model the cost of entire paths through the data plane. In two case studies, we use our framework to discover and model selected behavior for a DPDK-based software target and for the NFP-4000 SmartNIC platform.

查看原文本刊更多论文

可再现数据平面性能建模框架

像P4这样的数据平面编程语言引发了数据平面中大量的新应用程序。动态的、不断变化的环境使得理解在特定数据平面目标中运行程序时可以预期的性能变得非常困难。然而，了解这一点对于网络运营商在升级网络时至关重要。我们提出了一个可重复分析和P4程序组件建模的框架。通过定义和生成实验的精确规格，我们将完全自动生成的组件与测试平台或特定目标的部件分开。测量结果用于自动导出性能模型。然后，这些可以用来比较测量值和理论性能，或者通过数据平面对整个路径的成本进行建模。在两个案例研究中，我们使用我们的框架来发现和建模基于dpdk的软件目标和NFP-4000 SmartNIC平台的选择行为。

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

Proceedings of the Symposium on Architectures for Networking and Communications Systems

自引率

0.00%

发文量