The Evolution of (Open Source) Data Processing

Technology

Description:

Beginning with MapReduce and its first popular open-source implementation in Apache Hadoop the data processing landscape has evolved quite a bit. Since then we have seen several paradigm shifts and open-source systems evolved to support new types of applications and to attract new audiences. We will follow developments using the example of the open-source stream processing system Apache Flink and in the end we will see how expressive APIs, support for event-driven applications, Flink SQL for seamless batch and stream processing, and a powerful runtime enable a wide range of applications.