Abstract
This chapter presents the results of the FlexPath network processor (NP) project. Based on observations on current NP implementations and relevant Internet traffic scenarios, a new NP architecture is defined that makes use of reconfigurable packet processing paths in order to improve the system performance. We propose to extend state-of-the-art processor-centric NP architectures with specific hardware units in order to classify the incoming traffic into separate processing classes. For each traffic class, we can provide an optimized processing path, i.e. a functional unit traversal sequence within the NP. In addition, we propose to offload significant shares of the traffic to a dedicated hardware path in order to bypass the CPU cluster and save precious programmable processing resources. We also address the problem of multi-processor load balancing in the context of multi-core network processors. The concepts have been evaluated on an analytical and simulative level, and finally a demonstrator has been implemented on an FPGA in order to prove the claimed performance advantage by measurements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Agilent: Mixed Packet Size Throughput. http://advanced.comms.agilent.com/n2x/docs/insight/2001-08/TestingTips/1MxdPktSzThroughput.pdf (2001)
CAIDA: Anonymized OC-48 Traces. https://data.caida.org/datasets/oc48/oc48-original (2002)
CAIDA: Anonymized 2008 Internet Traces (OC-192), https://data.caida.org/datasets/passive-2008 (2008)
Dittmann, G., Herkersdorf, A.: Network processor load balancing for high-speed links. In: SPECTS 2002, San Diego, CA, USA (2002)
Govind, S., Govindarajan, R., Kuri, J.: Packet reordering in network processors. In: IPDPS 2007, Long Beach, CA, USA (2007)
Herkersdorf, A., Claus, C., Meitinger, M., Ohlendorf, R.: Reconfigurable processing units vs. reconfigurable interconnects. In: Dagstuhl Seminar on Dynamically Reconfigurable Architectures, Dagstuhl Seminar Proceedings 06141, Dagstuhl, Germany (2006)
Meitinger, M., Ohlendorf, R., Wild, T., Herkersdorf, A.: A programmable stream processing engine for packet manipulation in network processors. In: ISVLSI 2007, Porto Alegre, Brazil (2007)
Meitinger, M., Ohlendorf, R., Wild, T., Herkersdorf, A.: A hardware packet resequencer unit for network processors. In: ARCS 2008, Dresden, Germany (2008)
Meitinger, M., Ohlendorf, R., Wild, T., Herkersdorf, A.: FlexPath NP—a network processor architecture with flexible processing paths. In: SoC 2008, Tampere, Finland (2008)
Ohlendorf, R., Herkersdorf, A., Wild, T.: FlexPath NP—a network processor concept with application-driven flexible processing paths. In: CODES + ISSS 2005, Jersey City, NJ, USA (2005). http://doi.acm.org/10.1145/1084834.1084904
Ohlendorf, R., Wild, T., Meitinger, M., Rauchfuss, H., Herkersdorf, A.: Performance evaluation of RISC-based SoC platforms in network processing applications. In: IC-SAMOS 2006, Samos, Greece (2006)
Ohlendorf, R., Meitinger, M., Wild, T., Herkersdorf, A.: A packet classification technique for on-chip processing path selection. In: WASP 2007, Salzburg, Austria (2007)
Ohlendorf, R., Wild, T., Meitinger, M., Rauchfuss, H., Herkersdorf, A.: Simulated and measured performance evaluation of RISC-based SoC platforms in network processing applications. J. Syst. Architect. 53(10), 703–718 (2007). doi:10.1016/j.sysarc.2007.01.009
Ohlendorf, R., Meitinger, M., Wild, T., Herkersdorf, A.: A processing path dispatcher in network processor MPSoCs. IEEE Trans. VLSI Systems 16(10), 1335–1345 (2008). doi:10.1109/TVLSI.2008.2002048
Pionteck, T., Koch, R., Albrecht, C., Maehle, E., Meitinger, M., Ohlendorf, R., Wild, T., Herkersdorf, A.: SPP1148 booth: network processors. In: FPL 2008, Heidelberg, Germany (2008)
Shi, W., Kencl, L.: Sequence-preserving adaptive load balancers. In: ANCS 2006, San Jose, CA, USA (2006)
Shi, W., MacGregor, M., Gburzynski, P.: Load balancing for parallel forwarding. IEEE Trans. Networking 13(4), 790–801 (2005)
Sprint Academic Research Group: IP Data Analysis (2009). https://research.sprintlabs.com/packstat/packetoverview.php
Traboulsi, S., Meitinger, M., Ohlendorf, R., Herkersdorf, A.: An efficient hardware architecture for packet re-sequencing in network processor MPSoCs. In: DSD 2009, Patras, Greece (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer Science+Business Media B.V.
About this chapter
Cite this chapter
Ohlendorf, R., Meitinger, M., Wild, T., Herkersdorf, A. (2010). FlexPath NP—Flexible, Dynamically Reconfigurable Processing Paths in Network Processors. In: Platzner, M., Teich, J., Wehn, N. (eds) Dynamically Reconfigurable Systems. Springer, Dordrecht. https://doi.org/10.1007/978-90-481-3485-4_17
Download citation
DOI: https://doi.org/10.1007/978-90-481-3485-4_17
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-3484-7
Online ISBN: 978-90-481-3485-4
eBook Packages: EngineeringEngineering (R0)