High-speed IP address lookup using balanced multi-way trees

Hyesook Lim, Wonjung Kim, Bomi Lee, Changhoon Yim

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Rapid growth of the Internet traffic requires more bandwidth and high-speed packet processing in the Internet routers. As one of the major packet processing performed in routers, address lookup determines an output port using the destination IP address of incoming packets. Since routers should perform address lookups in real-time for hundred millions of incoming packets per second referring a huge routing table, address lookup is one of the most challenging operations. In this paper, we propose a multi-way search architecture for IP address lookup which shows very good performance in search speed. The performance evaluation results show that the proposed scheme requires a single 282 kbyte SRAM to store about 40,000 routing entries, and an address lookup is achieved by 5.9 memory accesses in average.

Original languageEnglish
Pages (from-to)1927-1935
Number of pages9
JournalComputer Communications
Volume29
Issue number11
DOIs
StatePublished - 26 Jul 2006

Keywords

  • Balanced tree
  • Binary prefix tree
  • IP address lookup
  • Memory access
  • Multi-way tree
  • Router

Fingerprint

Dive into the research topics of 'High-speed IP address lookup using balanced multi-way trees'. Together they form a unique fingerprint.

Cite this