sosp052-kotla - Zyzzyva: Speculative Byzantine Fault...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Zyzzyva: Speculative Byzantine Fault Tolerance Ramakrishna Kotla, Lorenzo Alvisi, Mike Dahlin, Allen Clement, and Edmund Wong Dept. of Computer Sciences University of Texas at Austin {kotla,lorenzo,dahlin,aclement,[email protected] ABSTRACT We present Zyzzyva, a protocol that uses speculation to re- duce the cost and simplify the design of Byzantine fault tolerant state machine replication. In Zyzzyva, replicas re- spond to a client’s request without first running an expensive three-phase commit protocol to reach agreement on the or- der in which the request must be processed. Instead, they optimistically adopt the order proposed by the primary and respond immediately to the client. Replicas can thus be- come temporarily inconsistent with one another, but clients detect inconsistencies, help correct replicas converge on a single total ordering of requests, and only rely on responses that are consistent with this total order. This approach al- lows Zyzzyva to reduce replication overheads to near their theoretical minima. Categories and Subject Descriptors D.4.5 [ Operating Systems ]: Reliability— Fault-tolerance ; D.4.7 [ Operating Systems ]: Organization and Design— Distributed systems ; H.3.4 [ Information Storage and Re- trieval ]: Systems and Software— Distributed systems General Terms Performance, Reliability Keywords Byzantine fault tolerance, Speculative execution, Replica- tion, Output commit 1. INTRODUCTION Three trends make Byzantine Fault Tolerant (BFT) repli- cation increasingly attractive for practical deployment. First, the growing value of data and and falling costs of hardware make it advantageous for service providers to trade increas- ingly inexpensive hardware for the peace of mind potentially provided by BFT replication. Second, mounting evidence of Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. SOSP’07, October 14–17, 2007, Stevenson, Washington, USA. Copyright 2007 ACM 978-1-59593-591-5/07/0010 ...$5.00. non-fail-stop behavior in real systems [2, 5, 6, 26, 29, 31, 35, 38, 39] suggest that BFT may yield significant benefits even without resorting to n-version programming [4, 15, 32]. Third, improvements to the state of the art in BFT replica- tion techniques [3, 9, 10, 17, 32, 40] make BFT replication increasingly practical by narrowing the gap between BFT replication costs and costs already being paid for non-BFT replication. For example, by default, the Google file system uses 3-way replication of storage, which is roughly the cost of BFT replication for f = 1 failures with 4 agreement nodes and 3 execution nodes [40]....
View Full Document

This note was uploaded on 12/08/2011 for the course CS 525 taught by Professor Gupta during the Spring '08 term at University of Illinois, Urbana Champaign.

Page1 / 14

sosp052-kotla - Zyzzyva: Speculative Byzantine Fault...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online