mardi 9 mai 2017

MapReduce

MapReduce is a programming model for processing large data sets. It is based on two functions commonly used in functional programming : map and reduce. The Map function processes key/value pairs to generate a set of intermediate key/value pairs and the Reduce function merges all the same intermediate values. The most popular implementation of the MapReduce model is the Hadoop framework, an open source software maintained by Apache Fundation, which allows applications to run on large clusters of several machines. The Hadoop framework transparently provides both reliability and data transfer. It partitions the data and computation over many of hosts and maintain the execution of application computations in parallel close to their data when possible. It also provides powerful distributed file system capabilities. Large scale data are broken down onto blocks. The map and reduce functions can be executed on these subsets.This provides scalability needed for big data processing.

Aucun commentaire:

Enregistrer un commentaire