北航云计算公开课05 mapreduce.docVIP

Map Reduce 11 / 12 ? ? ? ? ? ? A MapReduce job usually splits the input data-set into independent chunks. The chunks processed by the map tasks in a completely parallel manner. The framework sorts the outputs of the maps, which are then input to the reduce tasks. Typically both the input and the output of the job are stored in a file-system. Typically the worker nodes and the data nodes are the same. The MapReduce framework and the Hadoop Distributed File System (see HDFS Architecture are running on the same set of nodes. Map Reduce 12 / 12