Echtle, Klaus; Masum, A.:
A multiple bus broadcast protocol resilient to non-cooperative Byzantine faults
In: Proceedings of the Twenty-sixth International Symposium on Fault Tolerant Computing - Twenty-sixth International Symposium on Fault Tolerant Computing, June 25 - 27, 1996, Sendai, Japan - Los Alamitos: IEEE Computer Society Press, 1996, S. 158
1996Buchaufsatz/Kapitel in Tagungsband
Wirtschaftswissenschaften
Titel in Englisch:
A multiple bus broadcast protocol resilient to non-cooperative Byzantine faults
Autor*in:
Echtle, KlausUDE
LSF ID
5086
Sonstiges
der Hochschule zugeordnete*r Autor*in
;Masum, A.
Sprache des Textes:
Englisch
Erschienen in
Proceedings of the Twenty-sixth International Symposium on Fault Tolerant Computing
Konferenz
Twenty-sixth International Symposium on Fault Tolerant Computing, June 25 - 27, 1996, Sendai, Japan
Erscheinungsort:
Los Alamitos
Verlag:
IEEE Computer Society Press
Erscheinungsjahr:
1996
in:
S. 158
DOI
10.1109/FTCS.1996.534603

Abstract:

We describe a reliable broadcast protocol for multiple buses. It utilizes the benefits of a slightly restricted Byzantine fault model. Unlike common fault models we refrain from putting restrictions on the behavior of single node failures (i.e., fail omission assumption). Instead we make the assumption on the overall behavior of a set of faulty system components. By excluding extremely unlikely malicious cooperation we can reach uniform agreement on message delivery among faultless nodes at low cost. In the faultless case the execution time is bound by the maximum duration of a single broadcast message. In the presence of omission, timing and even non-cooperative Byzantine faults, both execution time and message number depend on the properties of the surviving network. In contrast to other known protocols our approach tolerates up to n-2 faulty nodes in a system of n nodes. Moreover, any number of bus faults and bus access unit faults are tolerated, provided that the network is not partitioned.