MapReduce: Simplified Data Processing on Large Clusters

MapReduce: The programming model and practice

Google’s MapReduce programming model — Revisited

Exploring Wikipedia with Apache Spark: A Live Coding Demo

Besides in-memory data, Apache Spark uses ideas from functional programming (immutable data, operations on data as functional transformations…) explaining why Scala is for the moment the lingua franca language of Apache Spark and Big Data.

Matei Zaharia, Spark inventor, explains the history of Spark starting from MapReduce and Hadoop.

The reason for Big Data is Machine Learning : MapReduce -> Hadoop -> BigData(Spark) -> Machine Learning

Apache Spark Architecture – Spark Cluster Architecture Explained

Putting Apache Spark Into Action with Jean Georges Perrin