CHAPTER 3Computation
In the previous chapter we set up a Hadoop integrated storage system, where we stored huge amounts of data to be used by a distributed computation engine. Hadoop MapReduce is the major distributed computation framework that has been used for a long time. Hadoop MapReduce is an actual open source implementation of MapReduce, supported by various types of companies and individuals. The reliability and results of Hadoop MapReduce for enterprise usage is outstanding among many of the distributed computation frameworks.
In this chapter, we will introduce the basic concept of MapReduce, and the details of implementing Hadoop MapReduce. Hadoop MapReduce is easily understood by engineers who are familiar with distributed computation or high performance computing. If you have sufficient knowledge in that area, please skip this first section about the basics of MapReduce.
BASICS OF HADOOP MAPREDUCE
Hadoop MapReduce is an open source version of a distributed computational framework originally introduced by Google. MapReduce enables you to easily write general distributed applications on Hadoop, and the MapReduce computational model is so general that you can write almost any type of process logic used in enterprise. Here we will explain the basic concepts and purposes of the MapReduce ...
Get Professional Hadoop now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
