HybridSFC: Accelerating Service Function Chains with Parallelism

Yang Zhang; Zhi Li Zhang; Bo Han

doi:10.1109/NFV-SDN47374.2019.9040088

HybridSFC: Accelerating Service Function Chains with Parallelism

Yang Zhang, Zhi Li Zhang, Bo Han

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

Network Function Virtualization (NFV) coupled with Software Defined Networking (SDN) creates new opportunities as well as substantial challenges such as increased Service Function Chain (SFC) latency and reduced throughput. In this paper, we present HybridSFC, a framework that explores the opportunities of parallel packet processing at both traffic level and Network Function (NF) level. It incorporates innovative control and data-plane mechanisms that partition and convert a sequential chain into several (finer-grained) SFClets that can be executed in parallel on multiple cores and servers. HybridSFC is practical in that it can handle NFs spanning multiple servers and requires no modifications to existing NFs. Experiments show that HybridSFC reduces latency up to 51% with 7% CPU overhead, and a 1.42×-1.87× improvement in overall system throughput.

Original language	English (US)
Title of host publication	IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings
Editors	Larry Horner, Kurt Tutschku, Fabrizio Granelli, Yuji Sekiya, Marco Tacca, Deval Bhamare, Helge Parzyjegla
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728145457
DOIs	https://doi.org/10.1109/NFV-SDN47374.2019.9040088
State	Published - Nov 2019
Event	2019 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Dallas, United States Duration: Nov 12 2019 → Nov 14 2019

Publication series

Name	IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings

Conference

Conference	2019 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019
Country/Territory	United States
City	Dallas
Period	11/12/19 → 11/14/19

Bibliographical note

Funding Information:
VIII. ACKNOWLEDGMENT The research was supported in part by NSF under Grants CNS-1618339, CNS-1617729, CNS-1814322, and CNS-1836772.

Publisher Copyright:
© 2019 IEEE.

Access

10.1109/NFV-SDN47374.2019.9040088

OpenUrl availability

Full text

Cite this

Zhang, Y., Zhang, Z. L., & Han, B. (2019). HybridSFC: Accelerating Service Function Chains with Parallelism. In L. Horner, K. Tutschku, F. Granelli, Y. Sekiya, M. Tacca, D. Bhamare, & H. Parzyjegla (Eds.), IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings Article 9040088 (IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NFV-SDN47374.2019.9040088

HybridSFC: Accelerating Service Function Chains with Parallelism. / Zhang, Yang; Zhang, Zhi Li; Han, Bo.
IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings. ed. / Larry Horner; Kurt Tutschku; Fabrizio Granelli; Yuji Sekiya; Marco Tacca; Deval Bhamare; Helge Parzyjegla. Institute of Electrical and Electronics Engineers Inc., 2019. 9040088 (IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, Y, Zhang, ZL & Han, B 2019, HybridSFC: Accelerating Service Function Chains with Parallelism. in L Horner, K Tutschku, F Granelli, Y Sekiya, M Tacca, D Bhamare & H Parzyjegla (eds), IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings., 9040088, IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019, Dallas, United States, 11/12/19. https://doi.org/10.1109/NFV-SDN47374.2019.9040088

Zhang Y, Zhang ZL, Han B. HybridSFC: Accelerating Service Function Chains with Parallelism. In Horner L, Tutschku K, Granelli F, Sekiya Y, Tacca M, Bhamare D, Parzyjegla H, editors, IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 9040088. (IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings). doi: 10.1109/NFV-SDN47374.2019.9040088

Zhang, Yang ; Zhang, Zhi Li ; Han, Bo. / HybridSFC : Accelerating Service Function Chains with Parallelism. IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings. editor / Larry Horner ; Kurt Tutschku ; Fabrizio Granelli ; Yuji Sekiya ; Marco Tacca ; Deval Bhamare ; Helge Parzyjegla. Institute of Electrical and Electronics Engineers Inc., 2019. (IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings).

@inproceedings{a37f171db9584b6b80bd140d48ddc3a5,

title = "HybridSFC: Accelerating Service Function Chains with Parallelism",

abstract = "Network Function Virtualization (NFV) coupled with Software Defined Networking (SDN) creates new opportunities as well as substantial challenges such as increased Service Function Chain (SFC) latency and reduced throughput. In this paper, we present HybridSFC, a framework that explores the opportunities of parallel packet processing at both traffic level and Network Function (NF) level. It incorporates innovative control and data-plane mechanisms that partition and convert a sequential chain into several (finer-grained) SFClets that can be executed in parallel on multiple cores and servers. HybridSFC is practical in that it can handle NFs spanning multiple servers and requires no modifications to existing NFs. Experiments show that HybridSFC reduces latency up to 51% with 7% CPU overhead, and a 1.42×-1.87× improvement in overall system throughput.",

author = "Yang Zhang and Zhang, {Zhi Li} and Bo Han",

note = "Funding Information: VIII. ACKNOWLEDGMENT The research was supported in part by NSF under Grants CNS-1618339, CNS-1617729, CNS-1814322, and CNS-1836772. Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 ; Conference date: 12-11-2019 Through 14-11-2019",

year = "2019",

month = nov,

doi = "10.1109/NFV-SDN47374.2019.9040088",

language = "English (US)",

series = "IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Larry Horner and Kurt Tutschku and Fabrizio Granelli and Yuji Sekiya and Marco Tacca and Deval Bhamare and Helge Parzyjegla",

booktitle = "IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings",

}

TY - GEN

T1 - HybridSFC

T2 - 2019 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019

AU - Zhang, Yang

AU - Zhang, Zhi Li

AU - Han, Bo

PY - 2019/11

Y1 - 2019/11

N2 - Network Function Virtualization (NFV) coupled with Software Defined Networking (SDN) creates new opportunities as well as substantial challenges such as increased Service Function Chain (SFC) latency and reduced throughput. In this paper, we present HybridSFC, a framework that explores the opportunities of parallel packet processing at both traffic level and Network Function (NF) level. It incorporates innovative control and data-plane mechanisms that partition and convert a sequential chain into several (finer-grained) SFClets that can be executed in parallel on multiple cores and servers. HybridSFC is practical in that it can handle NFs spanning multiple servers and requires no modifications to existing NFs. Experiments show that HybridSFC reduces latency up to 51% with 7% CPU overhead, and a 1.42×-1.87× improvement in overall system throughput.

AB - Network Function Virtualization (NFV) coupled with Software Defined Networking (SDN) creates new opportunities as well as substantial challenges such as increased Service Function Chain (SFC) latency and reduced throughput. In this paper, we present HybridSFC, a framework that explores the opportunities of parallel packet processing at both traffic level and Network Function (NF) level. It incorporates innovative control and data-plane mechanisms that partition and convert a sequential chain into several (finer-grained) SFClets that can be executed in parallel on multiple cores and servers. HybridSFC is practical in that it can handle NFs spanning multiple servers and requires no modifications to existing NFs. Experiments show that HybridSFC reduces latency up to 51% with 7% CPU overhead, and a 1.42×-1.87× improvement in overall system throughput.

UR - http://www.scopus.com/inward/record.url?scp=85082997680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85082997680&partnerID=8YFLogxK

U2 - 10.1109/NFV-SDN47374.2019.9040088

DO - 10.1109/NFV-SDN47374.2019.9040088

M3 - Conference contribution

AN - SCOPUS:85082997680

T3 - IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings

BT - IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2019 - Proceedings

A2 - Horner, Larry

A2 - Tutschku, Kurt

A2 - Granelli, Fabrizio

A2 - Sekiya, Yuji

A2 - Tacca, Marco

A2 - Bhamare, Deval

A2 - Parzyjegla, Helge

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 12 November 2019 through 14 November 2019

ER -

HybridSFC: Accelerating Service Function Chains with Parallelism

Abstract

Publication series

Conference

Bibliographical note

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this