Speeding Up Spark
A slow spark query can be painful, especially when spark describes itself as a solution to speeding up big data processes. In this post we equate a spark table to a poorly designed employee directory and continously improve it until we achieve more than a 20x speed up in performance.
Please click this link to view the post.
This post is hosted on databricks. It was made using the databricks community edition. To get the most out of this post please setup a free account and import the notebook into your environment.