FlashTrie: Hash-based prefix-compressed trie for ip route lookup beyond 100Gbps

Masanori Bando, H. Jonathan Chao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

It is becoming apparent that the next generation IP route lookup architecture needs to achieve speeds of 100-Gbps and beyond while supporting both IPv4 and IPv6 with fast real-time updates to accommodate ever-growing routing tables. Some of the proposed multibit-trie based schemes, such as Tree Bitmap [1], have been used in today's high-end routers. However, their large data structure often requires multiple external memory accesses for each route lookup. A pipelining technique is widely used to achieve high-speed lookup with a cost of using many external memory chips. Pipelining also often leads to poor memory load-balancing. In this paper, we propose a new IP route lookup architecture called FlashTrie that overcomes the shortcomings of the multibit-trie based approach. We use a hash-based membership query to limit off-chip memory accesses per lookup to one and to balance memory utilization among the memory modules. We also develop a new data structure called Prefix-Compressed Trie that reduces the size of a bitmap by more than 80%. Our simulation and implementation results show that FlashTrie can achieve 160-Gbps worst-case throughput while simultaneously supporting 2-M prefixes for IPv4 and 279-k prefixes for IPv6 using one FPGA chip and four DDR3 SDRAM chips. FlashTrie also supports incremental real-time updates.

Original languageEnglish (US)
Title of host publication2010 Proceedings IEEE INFOCOM
DOIs
StatePublished - 2010
EventIEEE INFOCOM 2010 - San Diego, CA, United States
Duration: Mar 14 2010Mar 19 2010

Other

OtherIEEE INFOCOM 2010
CountryUnited States
CitySan Diego, CA
Period3/14/103/19/10

Fingerprint

Data storage equipment
Data structures
Routers
Resource allocation
Field programmable gate arrays (FPGA)
Throughput
Costs

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

FlashTrie : Hash-based prefix-compressed trie for ip route lookup beyond 100Gbps. / Bando, Masanori; Chao, H. Jonathan.

2010 Proceedings IEEE INFOCOM. 2010. 5462142.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bando, M & Chao, HJ 2010, FlashTrie: Hash-based prefix-compressed trie for ip route lookup beyond 100Gbps. in 2010 Proceedings IEEE INFOCOM., 5462142, IEEE INFOCOM 2010, San Diego, CA, United States, 3/14/10. https://doi.org/10.1109/INFCOM.2010.5462142
@inproceedings{a8c93eaa78b443c6aa35d1a9b2bc3a25,
title = "FlashTrie: Hash-based prefix-compressed trie for ip route lookup beyond 100Gbps",
abstract = "It is becoming apparent that the next generation IP route lookup architecture needs to achieve speeds of 100-Gbps and beyond while supporting both IPv4 and IPv6 with fast real-time updates to accommodate ever-growing routing tables. Some of the proposed multibit-trie based schemes, such as Tree Bitmap [1], have been used in today's high-end routers. However, their large data structure often requires multiple external memory accesses for each route lookup. A pipelining technique is widely used to achieve high-speed lookup with a cost of using many external memory chips. Pipelining also often leads to poor memory load-balancing. In this paper, we propose a new IP route lookup architecture called FlashTrie that overcomes the shortcomings of the multibit-trie based approach. We use a hash-based membership query to limit off-chip memory accesses per lookup to one and to balance memory utilization among the memory modules. We also develop a new data structure called Prefix-Compressed Trie that reduces the size of a bitmap by more than 80{\%}. Our simulation and implementation results show that FlashTrie can achieve 160-Gbps worst-case throughput while simultaneously supporting 2-M prefixes for IPv4 and 279-k prefixes for IPv6 using one FPGA chip and four DDR3 SDRAM chips. FlashTrie also supports incremental real-time updates.",
author = "Masanori Bando and Chao, {H. Jonathan}",
year = "2010",
doi = "10.1109/INFCOM.2010.5462142",
language = "English (US)",
isbn = "9781424458363",
booktitle = "2010 Proceedings IEEE INFOCOM",

}

TY - GEN

T1 - FlashTrie

T2 - Hash-based prefix-compressed trie for ip route lookup beyond 100Gbps

AU - Bando, Masanori

AU - Chao, H. Jonathan

PY - 2010

Y1 - 2010

N2 - It is becoming apparent that the next generation IP route lookup architecture needs to achieve speeds of 100-Gbps and beyond while supporting both IPv4 and IPv6 with fast real-time updates to accommodate ever-growing routing tables. Some of the proposed multibit-trie based schemes, such as Tree Bitmap [1], have been used in today's high-end routers. However, their large data structure often requires multiple external memory accesses for each route lookup. A pipelining technique is widely used to achieve high-speed lookup with a cost of using many external memory chips. Pipelining also often leads to poor memory load-balancing. In this paper, we propose a new IP route lookup architecture called FlashTrie that overcomes the shortcomings of the multibit-trie based approach. We use a hash-based membership query to limit off-chip memory accesses per lookup to one and to balance memory utilization among the memory modules. We also develop a new data structure called Prefix-Compressed Trie that reduces the size of a bitmap by more than 80%. Our simulation and implementation results show that FlashTrie can achieve 160-Gbps worst-case throughput while simultaneously supporting 2-M prefixes for IPv4 and 279-k prefixes for IPv6 using one FPGA chip and four DDR3 SDRAM chips. FlashTrie also supports incremental real-time updates.

AB - It is becoming apparent that the next generation IP route lookup architecture needs to achieve speeds of 100-Gbps and beyond while supporting both IPv4 and IPv6 with fast real-time updates to accommodate ever-growing routing tables. Some of the proposed multibit-trie based schemes, such as Tree Bitmap [1], have been used in today's high-end routers. However, their large data structure often requires multiple external memory accesses for each route lookup. A pipelining technique is widely used to achieve high-speed lookup with a cost of using many external memory chips. Pipelining also often leads to poor memory load-balancing. In this paper, we propose a new IP route lookup architecture called FlashTrie that overcomes the shortcomings of the multibit-trie based approach. We use a hash-based membership query to limit off-chip memory accesses per lookup to one and to balance memory utilization among the memory modules. We also develop a new data structure called Prefix-Compressed Trie that reduces the size of a bitmap by more than 80%. Our simulation and implementation results show that FlashTrie can achieve 160-Gbps worst-case throughput while simultaneously supporting 2-M prefixes for IPv4 and 279-k prefixes for IPv6 using one FPGA chip and four DDR3 SDRAM chips. FlashTrie also supports incremental real-time updates.

UR - http://www.scopus.com/inward/record.url?scp=77953315191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953315191&partnerID=8YFLogxK

U2 - 10.1109/INFCOM.2010.5462142

DO - 10.1109/INFCOM.2010.5462142

M3 - Conference contribution

AN - SCOPUS:77953315191

SN - 9781424458363

BT - 2010 Proceedings IEEE INFOCOM

ER -