Skip to main navigation Skip to search Skip to main content

Field domain segmentation approach to filter encoding for efficient packet classification with TCAM

Derek Pao, Peng Zhou, Bin Liu, Xin Zhang

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Filter encoding can effectively enhance the efficiency of TCAM-based packet classification. However, additional complexity will be incurred in the filter table update operations. It has been shown that the average update cost of the prefix inclusion coding (PIC) scheme is very low but the worst case update cost can be significantly higher. In this paper we shall present a domain segmentation approach to enhance the performance of PIC. By dividing the field value domain into multiple segments, the mapping of field values to code points can be more structural and help to avoid massive code-point relocation in the event of new insertions. Moreover, the codeword lookup for the address fields can be largely simplified and can be implemented in SRAM rather than using TCAM. The lookup rate of the search engine can be improved to handle 40Gbps OC-768 line rate.
Original languageEnglish
Title of host publicationProceedings of the 7th IASTED International Conferences on Wireless and Optical Communications, WOC 2007
Pages136-142
Publication statusPublished - 2007
Event7th IASTED International Conferences on Wireless and Optical Communications, WOC 2007 - Montreal, QC, Canada
Duration: 30 May 20071 Jun 2007

Conference

Conference7th IASTED International Conferences on Wireless and Optical Communications, WOC 2007
PlaceCanada
CityMontreal, QC
Period30/05/071/06/07

Research Keywords

  • Domain segmentation
  • Filter encoding
  • Incremental update
  • Packet classification
  • Prefix inclusion coding
  • Ternary CAM

Fingerprint

Dive into the research topics of 'Field domain segmentation approach to filter encoding for efficient packet classification with TCAM'. Together they form a unique fingerprint.

Cite this