Benchmarking "Hello, World!"

Abstract

As more and more software moves off the desktop and into data centers, and more and more cell phones use server requests as the other half of apps, observation tools for large-scale distributed transaction systems are not keeping up. This makes it tempting to look under the lamppost using simpler tools. You will waste a lot of high-pressure time following that path when you have a sudden complex performance crisis. Instead, know what each tool you use is blind to, know what information you need to understand a performance problem, and then look for tools that can actually observe that information directly.