About

My name is Michael Kamprath, and I have worked in the scientific computing and big data space for a number of years. While I have also been a user of distributed computing systems, I had less of a command as to what went into setting up and managing a compute cluster. So, I decided to build one myself. This site documents my journey to build a home brewed big data compute cluster. While services such as AWS allow you to bring up a compute cluster with a few keystrokes, the goal of this journey is to create a cluster with real iron – economically, of course. Topics covered include server administration, hardware design, and big data analysis techniques.