A MapReduce iteration framework in local parallel and message synchronization
Wang T(王挺); Zhang HL(张华良); Ceng P(曾鹏)
In this paper, the redesign of the computing model of MapReduce, ensure the existing calculation models compatible with the old MapReduce operation. At the same time, the framework used the message synchronization mechanism to implement state data changing interaction tasks in Parallel Layer. Compared to the original MapReduce operation, greatly reduces the processing time of the MapReduce iterative algorithm.