Fast genuine generalized consensus

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Consensus (agreeing on a sequence of commands) is central to the operation and performance of distributed systems. A well-known solution to consensus is Fast Paxos. In a recent paper, Lamport enhances Fast Paxos by leveraging the commutativity of concurrent commands. The new primitive, called Generalized Paxos, reduces the collision rate, and thus the latency of Fast Paxos. However if a collision occurs, Generalized Paxos needs four communication steps to recover, which is slower than Fast Paxos. This paper presents FGGC, a novel consensus algorithm that reduces recovery delay when a collision occurs to one. FGGC tolerates f < n/2 replicas crashes, and during failure-free runs, processes learn commands in two steps if all commands commute, and three steps otherwise; this is optimal. Moreover, as long as no fault occurs, FGGC needs only f + 1 replicas to progress.

Original languageEnglish
Title of host publicationProceedings - 2011 30th IEEE International Symposium on Reliable Distributed Systems, SRDS 2011
Pages255-264
Number of pages10
DOIs
Publication statusPublished - 14 Dec 2011
Externally publishedYes
Event2011 30th IEEE International Symposium on Reliable Distributed Systems, SRDS 2011 - Madrid, Spain
Duration: 4 Oct 20117 Oct 2011

Publication series

NameProceedings of the IEEE Symposium on Reliable Distributed Systems
ISSN (Print)1060-9857

Conference

Conference2011 30th IEEE International Symposium on Reliable Distributed Systems, SRDS 2011
Country/TerritorySpain
CityMadrid
Period4/10/117/10/11

Keywords

  • algorithms
  • consensus
  • distributed systems
  • fault-tolerance
  • reliability

Fingerprint

Dive into the research topics of 'Fast genuine generalized consensus'. Together they form a unique fingerprint.

Cite this