Basics

Faster is a framework designed to make distributed computing easier. It uses distributed datasets called FDDs (Fast Distributed Dataset) as a interface between the programmer and what is going on in the distributed environment. In order to manipulate FDDs data, it offer several high level functions inherited from functional programming.

The Data flow usually comprises of:

• Input Data
• Apply Function(s)
• Output Result

Data Input

Data can be inserted into a FDD dataset from memmory of from file.

Data Output

When your programm is done processing data there is two options: collect the data from a FDD or write it to the file system.