Reliable communication in the presence of failures
ACM Transactions on Computer Systems (TOCS)
Preserving and using context information in interprocess communication
ACM Transactions on Computer Systems (TOCS)
Distributed systems
Impossibility of distributed consensus with one faulty process
Journal of the ACM (JACM)
Reaching Agreement in the Presence of Faults
Journal of the ACM (JACM)
ACM Transactions on Computer Systems (TOCS)
Delta Four: A Generic Architecture for Dependable Distributed Computing
Delta Four: A Generic Architecture for Dependable Distributed Computing
A High Performance Totally Ordered Multicast Protocol
Selected Papers from the International Workshop on Theory and Practice in Distributed Systems
FTCS '95 Proceedings of the Twenty-Fifth International Symposium on Fault-Tolerant Computing
Streets of Byzantium: Network Architectures for Fast Reliable Broadcasts
IEEE Transactions on Software Engineering
Avoiding Malicious Byzantine Faults by a New Signature Generation Technique
EDCC-3 Proceedings of the Third European Dependable Computing Conference on Dependable Computing
Hi-index | 0.00 |
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.