Network-assisted raft consensus algorithm

Yang Zhang, Bo Han, Zhi-Li Zhang, Vijay Gopalakrishnan

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

23 Scopus citations

Abstract

Consensus is a fundamental problem in distributed computing. In this poster, we ask the following question: Can we partially offload the execution of a consensus algorithm to the network to improve its performance? We argue for an affirmative answer by proposing a network-assisted implementation of the Raft consensus algorithm. Our approach reduces consensus latency, is failure-aware, and does not sacrifice correctness or scalability. In order to enable Raft-aware forwarding and quick response, we use P4-based programmable switches and offload partial Raft functionality to the switch. We demonstrate the efficacy of our approach and performance improvements it offers via a prototype implementation.

Original languageEnglish (US)
Title of host publicationSIGCOMM Posters and Demos 2017 - Proceedings of the 2017 SIGCOMM Posters and Demos, Part of SIGCOMM 2017
PublisherAssociation for Computing Machinery, Inc
Pages94-96
Number of pages3
ISBN (Electronic)9781450350570
DOIs
StatePublished - Aug 22 2017
EventACM SIGCOMM 2017 Conference - Los Angeles, United States
Duration: Aug 22 2017Aug 24 2017

Publication series

NameSIGCOMM Posters and Demos 2017 - Proceedings of the 2017 SIGCOMM Posters and Demos, Part of SIGCOMM 2017

Other

OtherACM SIGCOMM 2017 Conference
Country/TerritoryUnited States
CityLos Angeles
Period8/22/178/24/17

Bibliographical note

Publisher Copyright:
© 2017 ACM.

Keywords

  • Consensus
  • P4
  • Programmable networks
  • Raft algorithm
  • SDN

Fingerprint

Dive into the research topics of 'Network-assisted raft consensus algorithm'. Together they form a unique fingerprint.

Cite this