research-article

On runtime management in multi-core packet processing systems

Authors:

Qiang Wu,

Tilman WolfAuthors Info & Claims

ANCS '08: Proceedings of the 4th ACM/IEEE Symposium on Architectures for Networking and Communications Systems

Pages 69 - 78

https://doi.org/10.1145/1477942.1477953

Published: 06 November 2008 Publication History

Get Access

Abstract

Computer networks require increasingly complex packet processing in the data path to adapt to new functionality requirements. To meet performance demands, packet processing systems on routers employ multiple processor cores. We investigate the design of an efficient run-time management system that handles the allocation of processing tasks to processor cores. Using run-time profiling information about processing requirements and traffic characteristics, the system is able to adapt to dynamic changes in the workload and balance the utilization of all processing resources to maximize throughput. We present a prototype implementation of our system that is based on the Click modular router. Our results show that our prototype system can adapt to changing workloads and process computationally demanding packets at 1.32 times higher data rates than SMP Click.

References

[1]

Anderson, T., Peterson, L., Shenker, S., and Turner, J. Overcoming the Internet impasse through virtualization. Computer 38, 4 (Apr. 2005), 34--41.

Digital Library

Google Scholar

[2]

Calvert, K. L., Griffioen, J., and Wen, S. Lightweight network support for scalable end-to-end services. In SIGCOMM '02: Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications (Pittsburgh, PA, Aug. 2002), pp. 265--278.

Digital Library

Google Scholar

[3]

Chen, B., and Morris, R. Flexible control of parallelism in a multiprocessor PC router. In Proc. of the General Track: 2002 USENIX Annual Technical Conference (Monterey, CA, June 2001), pp. 333--346.

Digital Library

Google Scholar

[4]

Cisco Systems, Inc. The Cisco QuantumFlow Processor: CiscoŠs Next Generation Network Processor. San Jose, CA, Feb. 2008.

Google Scholar

[5]

Decasper, D., Dittia, Z., Parulkar, G., and Plattner, B. Router Plugins - a modular and extensible software framework for modern high performance integrated services routers. In Proc. of ACM SIGCOMM 98 (Vancouver, BC, Sept. 1998), pp. 229--240.

Digital Library

Google Scholar

[6]

Eatherton, W. The push of network processing to the top of the pyramid. In Keynote Presentation at ACM/IEEE Symposium on Architectures for Networking and Communication Systems (ANCS) (Princeton, NJ, Oct. 2005).

Google Scholar

[7]

Feldmann, A. Internet clean-slate design: what and why? SIGCOMM Computer Communication Review 37, 3 (July 2007), 59--64.

Digital Library

Google Scholar

[8]

Ganapathy, S., and Wolf, T. Design of a network service architecture. In Proc. of Sixteenth IEEE International Conference on Computer Communications and Networks (ICCCN) (Honolulu, HI, Aug. 2007), pp. 754--759.

Crossref

Google Scholar

[9]

Goglin, S. D., Hooper, D., Kumar, A., and Yavatkar, R. Advanced software framework, tools, and languages for the IXP family. Intel Technology Journal 7, 4 (Nov. 2003), 64--76.

Google Scholar

[10]

Grohoski, G. Niagara2: A highly threaded server-on-a-chip. In Proc. of Symposium on High Performance Chips (HOT CHIPS 18 (Palo Alto, CA, Aug. 2006).

Google Scholar

[11]

Hadzic, I., Marcus, W. S., and Smith, J. M. On-the-fly programmable hardware for networks. In Proc. of IEEE Globecom 98 (Syndey, Australia, Nov. 1998).

Crossref

Google Scholar

[12]

Hutchinson, N. C., and Peterson, L. L. The x-kernel: An architecture for implementing network protocols. IEEE Transactions on Software Engineering 17, 1 (Jan. 1991), 64--76.

Digital Library

Google Scholar

[13]

Kohler, E., Morris, R., Chen, B., Jannotti, J., and Kaashoek, M. F. The Click modular router. ACM Transactions on Computer Systems 18, 3 (Aug. 2000), 263--297.

Digital Library

Google Scholar

[14]

Kokku, R., Riché, T., Kunze, A., Mudigonda, J., Jason, J., and Vin, H. A case for run-time adaptation in packet processing systems. In Proc. of the 2nd Workshop on Hot Topics in Networks (HOTNETS-II) (Cambridge, MA, Nov. 2003).

Google Scholar

[15]

Lockwood, J. W., McKeown, N., Watson, G., Gibb, G., Hartke, P., Naous, J., Raghuraman, R., and Luo, J. NetFPGA--an open platform for gigabit-rate network switching and routing. In MSE '07: Proceedings of the 2007 IEEE International Conference on Microelectronic Systems Education (San Diego, CA, June 2007), pp. 160--161.

Digital Library

Google Scholar

[16]

Mallik, A., and Memik, G. Automated task distribution in multicore network processors using statistical analysis. In Proc. of ACM/IEEE Symposium on Architectures for Networking and Communication Systems (ANCS) (Orlando, FL, Dec. 2007), pp. 67--76.

Digital Library

Google Scholar

[17]

Plishker, W., Ravindran, K., Shah, N., and Keutzer, K. Automated task allocation for network processors. In Proc. of Network System Design Conference (Oct. 2004), pp. 235--245.

Google Scholar

[18]

Shah, N., Plishker, W., Ravindran, K., and Keutzer, K. Np-click: A productive software development approach for network processors. IEEE Micro 24, 5 (Sept. 2004), 45--54.

Digital Library

Google Scholar

[19]

Spalink, T., Karlin, S., Peterson, L., and Gottlieb, Y. Building a robust software-based router using network processors. In Proc. of the 18th ACM Symposium on Operating Systems Principles (SOSP) (Banff, AB, Oct. 2001), pp. 216--229.

Digital Library

Google Scholar

[20]

Tennenhouse, D. L., and Wetherall, D. J. Towards an active network architecture. ACM SIGCOMM Computer Communication Review 26, 2 (Apr. 1996), 5--18.

Digital Library

Google Scholar

[21]

Turner, J. S. A proposed architecture for the GENI backbone platform. In Proc. of ACM/IEEE Symposium on Architectures for Networking and Communication Systems (ANCS) (San Jose, CA, Dec. 2006), pp. 1--10.

Digital Library

Google Scholar

[22]

Turner, J. S., Crowley, P., DeHart, J., Freestone, A., Heller, B., Kuhns, F., Kumar, S., Lockwood, J., Lu, J., Wilson, M., Wiseman, C., and Zar, D. Supercharging PlanetLab: a high performance, multi-application, overlay network platform. In SIGCOMM '07: Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications (Kyoto, Japan, Aug. 2007), pp. 85--96.

Digital Library

Google Scholar

[23]

Wolf, T., Weng, N., and Tai, C.-H. Run-time support for multi-core packet processing systems. IEEE Network 21, 4 (July 2007), 29--37.

Digital Library

Google Scholar

Cited By

View all

Iqbal MHolt JRyoo Jde Veciana GJohn L(2016)Dynamic Core Allocation and Packet Scheduling in Multicore Network ProcessorsIEEE Transactions on Computers10.1109/TC.2016.256083865:12(3646-3660)Online publication date: 1-Dec-2016
https://dl.acm.org/doi/10.1109/TC.2016.2560838
Watkins LRobinson WBeyah R(2015)Using Network Traffic to Infer Hardware StateACM Transactions on Embedded Computing Systems10.1145/270009414:3(1-22)Online publication date: 30-Apr-2015
https://dl.acm.org/doi/10.1145/2700094
Takano YKhan ATamura MIwashina SShimizu T(2014)Virtualization-Based Scaling Methods for Stateful Cellular Network Nodes Using Elastic Core ArchitectureProceedings of the 2014 IEEE 6th International Conference on Cloud Computing Technology and Science10.1109/CloudCom.2014.16(204-209)Online publication date: 15-Dec-2014
https://dl.acm.org/doi/10.1109/CloudCom.2014.16
Show More Cited By

Index Terms

On runtime management in multi-core packet processing systems
1. Computer systems organization
  1. Architectures
    1. Parallel architectures
2. Networks
  1. Network components
    1. Intermediate nodes
      1. Routers

Recommendations

A case for run-time adaptation in packet processing systems

Most packet processing applications receive and process multiple types of packets. Today, the processors available within packet processing systems are allocated to packet types at design time. In this paper, we explore the benefits and challenges of ...
A Parallel Packet Processing Runtime System on Multi-core Network Processors
DCABES '12: Proceedings of the 2012 11th International Symposium on Distributed Computing and Applications to Business, Engineering & Science

More and more network devices and chips commonly apply multi-core architectures to meet increasingly performance demands. But the lack of efficient program level parallelism and workload allocation in the packet processing system greatly limits the ...
Runtime Task Allocation in Multicore Packet Processing Systems

Computer networks require increasingly complex packet processing functions in the data plane to adapt to new requirements. To meet performance demands, packet processing systems on routers employ multiple processor cores. To efficiently utilize ...

Reviews

Reviewer: Dan Emanoil Grigoras

This paper addresses the issue of balancing the use of replicated computing resources in routers. The idea is that packets belong to different applications and therefore require different amounts of processing on the fly. A task can be associated with each type of packet and its estimated amount of computation. In fact, Wu and Wolf use a runtime profiler that allows real data to be extracted. Then, the utilization factor leads to the total amount of processing needed for each task. The authors' assumptions are somehow too simple, considering that the total amount of computation can be divided into duplicated tasks that are mapped to separate cores. The arrival pattern of packets should be considered in this respect. Packets that need the same type of processing or task may be rare or, on the contrary, arrive in bursts. At the same time, some packets may have higher priority. The evaluation consists of four systems and three scenarios. The first scenario has very little processing (five percent), the second is 50-50, and the third has the most computation (99 percent). The throughput performance for all three scenarios, run by all four systems, is discussed. The main result is that the third scenario has the best performance on the fourth system. While I agree with most of the authors' decisions, such as runtime profiling, I think that the traffic system is oversimplified. This leads to expected results. How does the system manage congestion__?__ Online Computing Reviews Service

Access critical reviews of Computing literature here

Become a reviewer for Computing Reviews.

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

ANCS '08: Proceedings of the 4th ACM/IEEE Symposium on Architectures for Networking and Communications Systems

November 2008

191 pages

ISBN:9781605583464

DOI:10.1145/1477942

General Chair:
Mark Franklin
Washington University in St. Louis
,
Program Chairs:
D. K. Panda
Ohio State University
,
Dimitri Stiliadis
Bell Laboratory

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 06 November 2008

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article

Funding Sources

National Science Foundation

Conference

ANCS '08

Sponsor:

ANCS '08: Symposium on Architecture for Networking and Communications Systems

November 6 - 7, 2008

California, San Jose

Acceptance Rates

ANCS '08 Paper Acceptance Rate 17 of 67 submissions, 25%;

Overall Acceptance Rate 88 of 314 submissions, 28%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

27
Total Citations
View Citations
361
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Iqbal MHolt JRyoo Jde Veciana GJohn L(2016)Dynamic Core Allocation and Packet Scheduling in Multicore Network ProcessorsIEEE Transactions on Computers10.1109/TC.2016.256083865:12(3646-3660)Online publication date: 1-Dec-2016
https://dl.acm.org/doi/10.1109/TC.2016.2560838
Watkins LRobinson WBeyah R(2015)Using Network Traffic to Infer Hardware StateACM Transactions on Embedded Computing Systems10.1145/270009414:3(1-22)Online publication date: 30-Apr-2015
https://dl.acm.org/doi/10.1145/2700094
Takano YKhan ATamura MIwashina SShimizu T(2014)Virtualization-Based Scaling Methods for Stateful Cellular Network Nodes Using Elastic Core ArchitectureProceedings of the 2014 IEEE 6th International Conference on Cloud Computing Technology and Science10.1109/CloudCom.2014.16(204-209)Online publication date: 15-Dec-2014
https://dl.acm.org/doi/10.1109/CloudCom.2014.16
Iqbal MHolt JRyoo JJohn LVeciance G(2013)Flow Migration on Multicore Network ProcessorsProceedings of the 2013 42nd International Conference on Parallel Processing10.1109/ICPP.2013.24(150-159)Online publication date: 1-Oct-2013
https://dl.acm.org/doi/10.1109/ICPP.2013.24
Chen XChasaki DWolf T(2013)External monitoring of highly parallel network processors2013 IEEE 14th International Conference on High Performance Switching and Routing (HPSR)10.1109/HPSR.2013.6602312(197-204)Online publication date: Jul-2013
https://doi.org/10.1109/HPSR.2013.6602312
Iqbal MJohn LWolf TMoore APrasanna V(2012)Efficient traffic aware power management in multicore communications processorsProceedings of the eighth ACM/IEEE symposium on Architectures for networking and communications systems10.1145/2396556.2396581(123-134)Online publication date: 29-Oct-2012
https://dl.acm.org/doi/10.1145/2396556.2396581
Wu QWolf T(2012)Runtime Task Allocation in Multicore Packet Processing SystemsIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2012.5623:10(1934-1943)Online publication date: 1-Oct-2012
https://dl.acm.org/doi/10.1109/TPDS.2012.56
Iqbal MJohn L(2012)Power and performance analysis of network traffic prediction techniquesProceedings of the 2012 IEEE International Symposium on Performance Analysis of Systems & Software10.1109/ISPASS.2012.6189212(112-113)Online publication date: 1-Apr-2012
https://dl.acm.org/doi/10.1109/ISPASS.2012.6189212
Li YShan LQiao X(2012)A Parallel Packet Processing Runtime System on Multi-core Network ProcessorsProceedings of the 2012 11th International Symposium on Distributed Computing and Applications to Business, Engineering & Science10.1109/DCABES.2012.59(67-71)Online publication date: 19-Oct-2012
https://dl.acm.org/doi/10.1109/DCABES.2012.59
Pinel FPecero JBouvry PKhan S(2011)A Review on Task Performance Prediction in Multi-core Based SystemsProceedings of the 2011 IEEE 11th International Conference on Computer and Information Technology10.1109/CIT.2011.107(615-620)Online publication date: 31-Aug-2011
https://dl.acm.org/doi/10.1109/CIT.2011.107
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

A case for run-time adaptation in packet processing systems

A Parallel Packet Processing Runtime System on Multi-core Network Processors

Runtime Task Allocation in Multicore Packet Processing Systems

Reviews

Access critical reviews of Computing literature here