There are several benefits of MapReduce over conventional data processing techniques, some of them being:
First, the model is easy to use, even for programmers without experience with distributed systems, since it hides the details of parallelization, fault-tolerance, locality optimization, and load balancing. MapReduce allows developers to write applications in their language of choice (Java, C#, Python, C++, R, etc.) while handling the details of parallelization behind the scenes.
Second, a large variety of problems are easily expressible as MapReduce computations.
For example, MapReduce is used for the generation of data for Google's production web search service, for sorting, for data mining, for machine learning, and many other systems.
Third, MapReduce enables scaling of applications across large clusters of machines comprising thousands of nodes, with fault-tolerance built-in for ultra-fast performance.
Some useful MapReduce links:
http://en.wikipedia.org/wiki/MapReduce
http://labs.google.com/papers/mapreduce.html
Some useful SQL-MapReduce links:
http://www.asterdata.com/resources/mapreduce.php
http://www.asterdata.com/resources/writing.php
