Broadcasting Messages in Fault-Tolerant Distributed Systems: the benefit of handling input-triggered and output-triggered suspicions differently
Broadcasting messages in fault-tolerant distributed systems: the benefit of handling input-triggered and output-triggered suspicions differently B. Charron-Bost, X. Defago, and A. Schiper ABSTRACT The paper investigates the two main and seemingly antagonistic approaches to broadcasting messages reliably in fault-tolerant distributed systems: the approach based on Reliable Broadcast, and the one based on View Synchronous Communication (or VSC for short). While VSC does more than Reliable Broadcast, this has a cost. We show that this cost can be reduced by exploiting the difference between __input-triggered__ and __output-triggered__ suspicions, and by replacing the standard VSC broadcast primitive by two broadcast primitives; one sensitive to input-triggered suspicions, and the other sensitive to output-triggered suspicions.
Record created on 2005-05-20, modified on 2016-08-08