Troubleshooting performance issues across distributed systems can be intimidating if you don’t know where to start, and it’s even harder when the system is running on hundreds or thousands of nodes. We’re well past the point of logging into random nodes and poking around hoping we spot the problem. It’s critical to have a methodology to follow as well as a deep understanding of the tools that are available to help you prove (or disprove) your mental model.

In this session, we’ll explore how to go about diagnosing performance problems you might run into, and teach you the tools and process for getting to the bottom of any issue, quickly — even when it’s one of the biggest distributed database deployments on the planet.