Hardware-Software Co-Design for Network Performance Measurement

Diagnosing performance problems in networks is important, for example to determine where packets experience high latency or loss. However, existing performance diagnoses are constrained by limited switch mechanisms for measurement. Alternatively, operators use endpoint information indirectly to infe...

Full description

Bibliographic Details
Main Authors: Walker, David, Rexford, Jennifer, Jeyakumar, Vimalkumar, Kim, Changhoon, Narayana Ganapathy, Srinivas, Sivaraman Kaushalram, Anirudh, Nathan, Vikram, Alizadeh Attar, Mohammadreza
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:en_US
Published: Association for Computing Machinery (ACM) 2017
Online Access:http://hdl.handle.net/1721.1/110716
https://orcid.org/0000-0003-4034-0918
https://orcid.org/0000-0002-0014-6742
_version_ 1826189253288132608
author Walker, David
Rexford, Jennifer
Jeyakumar, Vimalkumar
Kim, Changhoon
Narayana Ganapathy, Srinivas
Sivaraman Kaushalram, Anirudh
Nathan, Vikram
Alizadeh Attar, Mohammadreza
author2 Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
author_facet Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Walker, David
Rexford, Jennifer
Jeyakumar, Vimalkumar
Kim, Changhoon
Narayana Ganapathy, Srinivas
Sivaraman Kaushalram, Anirudh
Nathan, Vikram
Alizadeh Attar, Mohammadreza
author_sort Walker, David
collection MIT
description Diagnosing performance problems in networks is important, for example to determine where packets experience high latency or loss. However, existing performance diagnoses are constrained by limited switch mechanisms for measurement. Alternatively, operators use endpoint information indirectly to infer root causes for problematic latency or drops. Instead of designing piecemeal solutions to work around such switch restrictions, we believe that the right approach is to co-design language abstractions and switch hardware primitives for network performance measurement. This approach provides confidence that the switch primitives are sufficiently general, i.e., they can support a variety of existing and unanticipated use cases. We present a declarative query language that allows operators to ask a diverse set of network performance questions. We show that these queries can be implemented efficiently in switch hardware using a novel programmable key-value store primitive. Our preliminary evaluations show that our hardware design is feasible at modest chip area overhead relative to existing switching chips.
first_indexed 2024-09-23T08:11:53Z
format Article
id mit-1721.1/110716
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T08:11:53Z
publishDate 2017
publisher Association for Computing Machinery (ACM)
record_format dspace
spelling mit-1721.1/1107162022-09-23T11:34:12Z Hardware-Software Co-Design for Network Performance Measurement Walker, David Rexford, Jennifer Jeyakumar, Vimalkumar Kim, Changhoon Narayana Ganapathy, Srinivas Sivaraman Kaushalram, Anirudh Nathan, Vikram Alizadeh Attar, Mohammadreza Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Narayana Ganapathy, Srinivas Sivaraman Kaushalram, Anirudh Nathan, Vikram Alizadeh Attar, Mohammadreza Diagnosing performance problems in networks is important, for example to determine where packets experience high latency or loss. However, existing performance diagnoses are constrained by limited switch mechanisms for measurement. Alternatively, operators use endpoint information indirectly to infer root causes for problematic latency or drops. Instead of designing piecemeal solutions to work around such switch restrictions, we believe that the right approach is to co-design language abstractions and switch hardware primitives for network performance measurement. This approach provides confidence that the switch primitives are sufficiently general, i.e., they can support a variety of existing and unanticipated use cases. We present a declarative query language that allows operators to ask a diverse set of network performance questions. We show that these queries can be implemented efficiently in switch hardware using a novel programmable key-value store primitive. Our preliminary evaluations show that our hardware design is feasible at modest chip area overhead relative to existing switching chips. 2017-07-14T20:07:17Z 2017-07-14T20:07:17Z 2016-11 Article http://purl.org/eprint/type/ConferencePaper 978-1-4503-4661-0 http://hdl.handle.net/1721.1/110716 Narayana, Srinivas et al. “Hardware-Software Co-Design for Network Performance Measurement.” Proceedings of the 15th ACM Workshop on Hot Topics in Networks, Atlanta, GA, USA, 9-10 November, 2016. ACM Press, 2016. pp.190–196. https://orcid.org/0000-0003-4034-0918 https://orcid.org/0000-0002-0014-6742 en_US http://dx.doi.org/10.1145/3005745.3005775 Proceedings of the 15th ACM Workshop on Hot Topics in Networks - HotNets '16 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) MIT Web Domain
spellingShingle Walker, David
Rexford, Jennifer
Jeyakumar, Vimalkumar
Kim, Changhoon
Narayana Ganapathy, Srinivas
Sivaraman Kaushalram, Anirudh
Nathan, Vikram
Alizadeh Attar, Mohammadreza
Hardware-Software Co-Design for Network Performance Measurement
title Hardware-Software Co-Design for Network Performance Measurement
title_full Hardware-Software Co-Design for Network Performance Measurement
title_fullStr Hardware-Software Co-Design for Network Performance Measurement
title_full_unstemmed Hardware-Software Co-Design for Network Performance Measurement
title_short Hardware-Software Co-Design for Network Performance Measurement
title_sort hardware software co design for network performance measurement
url http://hdl.handle.net/1721.1/110716
https://orcid.org/0000-0003-4034-0918
https://orcid.org/0000-0002-0014-6742
work_keys_str_mv AT walkerdavid hardwaresoftwarecodesignfornetworkperformancemeasurement
AT rexfordjennifer hardwaresoftwarecodesignfornetworkperformancemeasurement
AT jeyakumarvimalkumar hardwaresoftwarecodesignfornetworkperformancemeasurement
AT kimchanghoon hardwaresoftwarecodesignfornetworkperformancemeasurement
AT narayanaganapathysrinivas hardwaresoftwarecodesignfornetworkperformancemeasurement
AT sivaramankaushalramanirudh hardwaresoftwarecodesignfornetworkperformancemeasurement
AT nathanvikram hardwaresoftwarecodesignfornetworkperformancemeasurement
AT alizadehattarmohammadreza hardwaresoftwarecodesignfornetworkperformancemeasurement