The art of joining in Spark

Practical tips to speedup Spark joins

I’ve met Apache Spark a few months ago and it has been love at first sight. My first thought was: “it’s incredible how something this powerful can be so easy to use, I just need to write a bunch of SQL queries!”. Indeed starting with Spark is very simple: it has very nice APIs in multiple languages (e.g. Scala, Python, Java), it’s virtually possible to…