Large Scale Data Processing in Hadoop Mapreduce Scenario: Time Estimation and Computation Models

Cloud Computing has brought a huge impact in IT industry. Computing resources are easier to get in Cloud Computing. Briefly speaking, Cloud Computing is a resource pool, which contains a masssive amount of interconnected computers. Under such background, in order to make full use of the network, Google initiated MapReduce model. This model is an implementation of Parallel Computing, which aims at processing large amount of data. Given certain computing resources and MapReduce model, this book gives some thinking about how to estimate the time consumption of a huge computation task. Based on classical Parallel Computing theories, this book proposed two models to estimate the time consumption. It also gives conclusions about what type of computation task is estimatable. The experiments in this book are easy to implement, which are very suitable references for Cloud Computing fans.