It’s easy to conduct a misleading benchmark, and notoriously hard to design a correct and rigorous enough one. Have you ever asked why?

In this talk we will discuss database benchmarking on example of PostgreSQL:

• What is the best model to think about benchmarking?
• What are the typical technical challenges? How much PostgreSQL details one needs to know to not mess up and draw right conclusions?
• How to analyze the results, and what does it have to do with statistics?