Replicated Processes in Manetho
This paper presents the processÂreplication protocol of Manetho, a system whose goal is to provide efficient, applicationÂtransparent fault tolerance to longÂrunning distributed computations. Manetho uses a new negative acknowledgment multicast protocol to enforce the same receipt order of application messages among all replicas of a process. The protocol depends on a combination of antecedence graph maintenance, a form of senderÂbased message logging, and the fact that the receivers of each multicast execute the same deterministic program. This combination allows our protocol to avoid the delay in application message delivery that is common in exist ing negativeÂacknowledgment multicast protocols, without giving up the advantage of requiring only a small number of control messages.
ftcs92.ps.pdf
openaccess
218.36 KB
Adobe PDF
90634ecf44cb1fc73e9a61f30c84d5e7