Serialization plays an important role in the performance of any distributed application. Formats that are slow to serialize objects into, or consume a large number of bytes, will greatly slow down the computation. Often, this will be the first thing you should tune to optimize a Spark application. The Java default serializer has very mediocre performance regarding runtime as well as the size of its results. Therefore the Spark team recommends to use the Kryo serializer instead.
The following code shows an example of how you can turn on Kryo and how you can register the classes that you will be serializing:
val conf =new SparkConf().setAppName(...).setMaster(...)