Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Fault Detection for Byzantine Quorum Systems (Extended Abstract)

Summary: Fault Detection for Byzantine Quorum Systems
(Extended Abstract)
Lorenzo Alvisi \Lambda Dahlia Malkhi y Evelyn Pierce z Michael Reiter x
In this paper we explore techniques to detect Byzantine server failures in
replicated data services. Our goal is to detect arbitrary failures of data servers
in a system where each client accesses the replicated data at only a subset
(quorum) of servers in each operation. In such a system, some correct servers
can be out­of­date after a write and thus can return values other than the most
up­to­date value in response to a client's read request, thus complicating the
task of determining the number of faulty servers in the system at any point
in time. We initiate the study of detecting server failures in this context, and
propose two statistical approaches for estimating the number of faulty servers
based on responses to read requests.
1 Introduction
Data replication is a well­known means of protecting against data unavailability
or corruption in the face of data server failures. When servers can suffer Byzan­
tine (i.e., arbitrary) failures, the foremost approach for protecting data is via state
machine replication [Sch90], in which every correct server receives and processes
every request in the same order, thereby producing the same output for each re­


Source: Alvisi, Lorenzo - Department of Computer Sciences, University of Texas at Austin


Collections: Computer Technologies and Information Sciences