Methodology, measurement and analysis of flow table update characteristics in hardware openflow switches

Maciej Kuźniar; Peter Perešíni; Dejan Kostić; Marco Canini

doi:10.1016/j.comnet.2018.02.014

Methodology, measurement and analysis of flow table update characteristics in hardware openflow switches

Maciej Kuźniar, Peter Perešíni, Dejan Kostić^*, Marco Canini

^*Corresponding author for this work

Computer, Electrical and Mathematical Sciences and Engineering

Research output: Contribution to journal › Article › peer-review

41 Scopus citations

Abstract

Software-Defined Networking (SDN) and OpenFlow are actively being standardized and deployed. These deployments rely on switches that come from various vendors and differ in terms of performance and available features. Understanding these differences and performance characteristics is essential for ensuring successful and safe deployments. We propose a systematic methodology for SDN switch performance analysis and devise a series of experiments based on this methodology. The methodology relies on sending a stream of rule updates, while relying on both observing the control plane view as reported by the switch and probing the data plane state to determine switch characteristics by comparing these views. We measure, report and explain the performance characteristics of flow table updates in six hardware OpenFlow switches. Our results describing rule update rates can help SDN designers make their controllers efficient. Further, we also highlight differences between the OpenFlow specification and its implementations, that if ignored, pose a serious threat to network security and correctness.

Original language	English (US)
Pages (from-to)	22-36
Number of pages	15
Journal	Computer Networks
Volume	136
DOIs	https://doi.org/10.1016/j.comnet.2018.02.014
State	Published - May 8 2018

Bibliographical note

Funding Information:
The research leading to these results has received funding from the European Research Council under the European Union's Seventh Framework Programme (FP7/ 2007–2013) / ERC grant agreement 259110. This research is (in part) supported by European Union's Horizon 2020 research and innovation programme under the ENDEAVOUR project (grant agreement 644960). This work is in part financially supported by the Swedish Foundation for Strategic Research.

Funding Information:
We would like to thank Dan Levin and Miguel Peón for helping us get remote access to some of the tested switches. We also thank the representatives of the Pica8 P-3290, NoviSwitch 1132 and Switch X vendors for their quick and extensive responses that helped us understand some observations we made. The research leading to these results has received funding from the European Research Council under the European Union’s Seventh Framework Programme ( FP7/ 2007–2013 ) / ERC grant agreement 259110 . This research is (in part) supported by European Union’s Horizon 2020 research and innovation programme under the ENDEAVOUR project (grant agreement 644960 ). This work is in part financially supported by the Swedish Foundation for Strategic Research. Maciej Kuzniar obtained a Ph.D. degree from EPFL in 2016 and a Master of Science degree in Computer Science from AGH University of Science and Technology in Krakow in 2011. His research focuses on Software Defined Networks, especially aspects affecting their reliability. Additionally, he is interested in the wider area of distributed systems and computer networks. He currently works at Google. Peter Perešíni ’s research interests include Software-Defined Networking (with the focus on correctness, testing, reliability, and performance), Distributed Systems, and Computer Networking in general. He obtained his Ph.D. from EPFL, Switzerland in 2016 and a Master of Science degree with distinction from Comenius University in Bratislava in 2011. Peter completed multiple internships at Google, working on different projects. Dejan Kostic is a Professor of Internetworking at the KTH Royal Institute of Technology, where he is the head of the Network Systems Laboratory. His research interests include Distributed Systems, Computer Networks, Operating Systems, and Mobile Computing. Dejan Kostic obtained his Ph.D. in Computer Science at the Duke University. He spent the last two years of his studies and a brief stay as a postdoctoral scholar at the University of California, San Diego. Marco Canini is an assistant professor of computer science at King Abdullah University of Science and Technology (KAUST). His research interests include software-defined networking and large-scale and distributed cloud computing. He received a Ph.D. in computer science and engineering from the University of Genoa. He is a member of IEEE, ACM and USENIX.

Publisher Copyright:
© 2018 Elsevier B.V.

Keywords

Flow table updates
Measurements
Software-defined networking
Switch

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1016/j.comnet.2018.02.014

Cite this

@article{e3b2081b99d2468ba56347226462190e,

title = "Methodology, measurement and analysis of flow table update characteristics in hardware openflow switches",

abstract = "Software-Defined Networking (SDN) and OpenFlow are actively being standardized and deployed. These deployments rely on switches that come from various vendors and differ in terms of performance and available features. Understanding these differences and performance characteristics is essential for ensuring successful and safe deployments. We propose a systematic methodology for SDN switch performance analysis and devise a series of experiments based on this methodology. The methodology relies on sending a stream of rule updates, while relying on both observing the control plane view as reported by the switch and probing the data plane state to determine switch characteristics by comparing these views. We measure, report and explain the performance characteristics of flow table updates in six hardware OpenFlow switches. Our results describing rule update rates can help SDN designers make their controllers efficient. Further, we also highlight differences between the OpenFlow specification and its implementations, that if ignored, pose a serious threat to network security and correctness.",

keywords = "Flow table updates, Measurements, Software-defined networking, Switch",

author = "Maciej Ku{\'z}niar and Peter Pere{\v s}{\'i}ni and Dejan Kosti{\'c} and Marco Canini",

note = "Funding Information: The research leading to these results has received funding from the European Research Council under the European Union's Seventh Framework Programme (FP7/ 2007–2013) / ERC grant agreement 259110. This research is (in part) supported by European Union's Horizon 2020 research and innovation programme under the ENDEAVOUR project (grant agreement 644960). This work is in part financially supported by the Swedish Foundation for Strategic Research. Funding Information: We would like to thank Dan Levin and Miguel Pe{\'o}n for helping us get remote access to some of the tested switches. We also thank the representatives of the Pica8 P-3290, NoviSwitch 1132 and Switch X vendors for their quick and extensive responses that helped us understand some observations we made. The research leading to these results has received funding from the European Research Council under the European Union{\textquoteright}s Seventh Framework Programme ( FP7/ 2007–2013 ) / ERC grant agreement 259110 . This research is (in part) supported by European Union{\textquoteright}s Horizon 2020 research and innovation programme under the ENDEAVOUR project (grant agreement 644960 ). This work is in part financially supported by the Swedish Foundation for Strategic Research. Maciej Kuzniar obtained a Ph.D. degree from EPFL in 2016 and a Master of Science degree in Computer Science from AGH University of Science and Technology in Krakow in 2011. His research focuses on Software Defined Networks, especially aspects affecting their reliability. Additionally, he is interested in the wider area of distributed systems and computer networks. He currently works at Google. Peter Pere{\v s}{\'i}ni {\textquoteright}s research interests include Software-Defined Networking (with the focus on correctness, testing, reliability, and performance), Distributed Systems, and Computer Networking in general. He obtained his Ph.D. from EPFL, Switzerland in 2016 and a Master of Science degree with distinction from Comenius University in Bratislava in 2011. Peter completed multiple internships at Google, working on different projects. Dejan Kostic is a Professor of Internetworking at the KTH Royal Institute of Technology, where he is the head of the Network Systems Laboratory. His research interests include Distributed Systems, Computer Networks, Operating Systems, and Mobile Computing. Dejan Kostic obtained his Ph.D. in Computer Science at the Duke University. He spent the last two years of his studies and a brief stay as a postdoctoral scholar at the University of California, San Diego. Marco Canini is an assistant professor of computer science at King Abdullah University of Science and Technology (KAUST). His research interests include software-defined networking and large-scale and distributed cloud computing. He received a Ph.D. in computer science and engineering from the University of Genoa. He is a member of IEEE, ACM and USENIX. Publisher Copyright: {\textcopyright} 2018 Elsevier B.V.",

year = "2018",

month = may,

day = "8",

doi = "10.1016/j.comnet.2018.02.014",

language = "English (US)",

volume = "136",

pages = "22--36",

journal = "Computer Networks",

issn = "1389-1286",

publisher = "Elsevier",

}

TY - JOUR

T1 - Methodology, measurement and analysis of flow table update characteristics in hardware openflow switches

AU - Kuźniar, Maciej

AU - Perešíni, Peter

AU - Kostić, Dejan

AU - Canini, Marco

N1 - Funding Information: The research leading to these results has received funding from the European Research Council under the European Union's Seventh Framework Programme (FP7/ 2007–2013) / ERC grant agreement 259110. This research is (in part) supported by European Union's Horizon 2020 research and innovation programme under the ENDEAVOUR project (grant agreement 644960). This work is in part financially supported by the Swedish Foundation for Strategic Research. Funding Information: We would like to thank Dan Levin and Miguel Peón for helping us get remote access to some of the tested switches. We also thank the representatives of the Pica8 P-3290, NoviSwitch 1132 and Switch X vendors for their quick and extensive responses that helped us understand some observations we made. The research leading to these results has received funding from the European Research Council under the European Union’s Seventh Framework Programme ( FP7/ 2007–2013 ) / ERC grant agreement 259110 . This research is (in part) supported by European Union’s Horizon 2020 research and innovation programme under the ENDEAVOUR project (grant agreement 644960 ). This work is in part financially supported by the Swedish Foundation for Strategic Research. Maciej Kuzniar obtained a Ph.D. degree from EPFL in 2016 and a Master of Science degree in Computer Science from AGH University of Science and Technology in Krakow in 2011. His research focuses on Software Defined Networks, especially aspects affecting their reliability. Additionally, he is interested in the wider area of distributed systems and computer networks. He currently works at Google. Peter Perešíni ’s research interests include Software-Defined Networking (with the focus on correctness, testing, reliability, and performance), Distributed Systems, and Computer Networking in general. He obtained his Ph.D. from EPFL, Switzerland in 2016 and a Master of Science degree with distinction from Comenius University in Bratislava in 2011. Peter completed multiple internships at Google, working on different projects. Dejan Kostic is a Professor of Internetworking at the KTH Royal Institute of Technology, where he is the head of the Network Systems Laboratory. His research interests include Distributed Systems, Computer Networks, Operating Systems, and Mobile Computing. Dejan Kostic obtained his Ph.D. in Computer Science at the Duke University. He spent the last two years of his studies and a brief stay as a postdoctoral scholar at the University of California, San Diego. Marco Canini is an assistant professor of computer science at King Abdullah University of Science and Technology (KAUST). His research interests include software-defined networking and large-scale and distributed cloud computing. He received a Ph.D. in computer science and engineering from the University of Genoa. He is a member of IEEE, ACM and USENIX. Publisher Copyright: © 2018 Elsevier B.V.

PY - 2018/5/8

Y1 - 2018/5/8

N2 - Software-Defined Networking (SDN) and OpenFlow are actively being standardized and deployed. These deployments rely on switches that come from various vendors and differ in terms of performance and available features. Understanding these differences and performance characteristics is essential for ensuring successful and safe deployments. We propose a systematic methodology for SDN switch performance analysis and devise a series of experiments based on this methodology. The methodology relies on sending a stream of rule updates, while relying on both observing the control plane view as reported by the switch and probing the data plane state to determine switch characteristics by comparing these views. We measure, report and explain the performance characteristics of flow table updates in six hardware OpenFlow switches. Our results describing rule update rates can help SDN designers make their controllers efficient. Further, we also highlight differences between the OpenFlow specification and its implementations, that if ignored, pose a serious threat to network security and correctness.

AB - Software-Defined Networking (SDN) and OpenFlow are actively being standardized and deployed. These deployments rely on switches that come from various vendors and differ in terms of performance and available features. Understanding these differences and performance characteristics is essential for ensuring successful and safe deployments. We propose a systematic methodology for SDN switch performance analysis and devise a series of experiments based on this methodology. The methodology relies on sending a stream of rule updates, while relying on both observing the control plane view as reported by the switch and probing the data plane state to determine switch characteristics by comparing these views. We measure, report and explain the performance characteristics of flow table updates in six hardware OpenFlow switches. Our results describing rule update rates can help SDN designers make their controllers efficient. Further, we also highlight differences between the OpenFlow specification and its implementations, that if ignored, pose a serious threat to network security and correctness.

KW - Flow table updates

KW - Measurements

KW - Software-defined networking

KW - Switch

UR - http://www.scopus.com/inward/record.url?scp=85042660375&partnerID=8YFLogxK

U2 - 10.1016/j.comnet.2018.02.014

DO - 10.1016/j.comnet.2018.02.014

M3 - Article

AN - SCOPUS:85042660375

SN - 1389-1286

VL - 136

SP - 22

EP - 36

JO - Computer Networks

JF - Computer Networks

ER -

Methodology, measurement and analysis of flow table update characteristics in hardware openflow switches

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this