Revisiting Route Caching: The World Should Be Flat

  • Changhoon Kim
  • Matthew Caesar
  • Alexandre Gerber
  • Jennifer Rexford
Conference paper

DOI: 10.1007/978-3-642-00975-4_1

Part of the Lecture Notes in Computer Science book series (LNCS, volume 5448)
Cite this paper as:
Kim C., Caesar M., Gerber A., Rexford J. (2009) Revisiting Route Caching: The World Should Be Flat. In: Moon S.B., Teixeira R., Uhlig S. (eds) Passive and Active Network Measurement. PAM 2009. Lecture Notes in Computer Science, vol 5448. Springer, Berlin, Heidelberg

Abstract

Internet routers’ forwarding tables (FIBs), which must be stored in expensive fast memory for high-speed packet forwarding, are growing quickly in size due to increased multihoming, finer-grained traffic engineering, and deployment of IPv6 and VPNs. To address this problem, several Internet architectures have been proposed to reduce FIB size by returning to the earlier approach of route caching: storing only the working set of popular routes in the FIB. This paper revisits route caching. We build upon previous work by studying flat, uni-class (/24) prefix caching, with modern traffic traces from more than 60 routers in a tier-1 ISP. We first characterize routers’ working sets and then evaluate route-caching performance under different cache replacement strategies and cache sizes. Surprisingly, despite the large number of deaggregated /24 subnets, caching uni-class prefixes can effectively curb the increase of FIB sizes. Moreover, uni-class prefixes substantially simplify a cache design by eliminating longest-prefix matching, enabling FIB design with slower memory technologies. Finally, by comparing our results with previous work, we show that the distribution of traffic across prefixes is becoming increasingly skewed, making route caching more appealing.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Changhoon Kim
    • 1
  • Matthew Caesar
    • 2
  • Alexandre Gerber
    • 3
  • Jennifer Rexford
    • 1
  1. 1.Princeton UniversityUSA
  2. 2.UIUCUSA
  3. 3.AT&T Labs–ResearchUSA

Personalised recommendations