Exploiting virtual synchrony in distributed systems
SOSP '87 Proceedings of the eleventh ACM Symposium on Operating systems principles
AMp: a highly parallel atomic multicast protocol
SIGCOMM '89 Symposium proceedings on Communications architectures & protocols
The Byzantine Generals Problem
ACM Transactions on Programming Languages and Systems (TOPLAS)
Notes on Data Base Operating Systems
Operating Systems, An Advanced Course
Total order broadcast and multicast algorithms: Taxonomy and survey
ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
An atomic broadcast protocol should meet the three properties of unanimity, order and termination. The protocol presented here assumes weak fail-silent Network Attachment Controllers (NACs) and a broadcast channel subject to omission failures. In a failure-free environment it consists of a single phase. The response time achieved is almost the same as for a simple broadcast. In case of receivers failures, the number of phases depends on failure occurrences. In case of a broadcaster failure all the correct receivers detect the failure and all the receivers ignore the broadcast. This protocol ensures that each correct NACs has the same view of the correct NACs' list.