Kotlin’s coroutines and Flow APIs make asynchronous programming elegant — but when things get slow, they can also make performance opaque. What’s actually happening behind all those suspend functions and dispatchers?

In this talk, we’ll explore what Kotlin’s concurrency features really look like under the microscope of Perfetto — Android’s modern performance tracing tool. You’ll see how coroutine scopes, dispatchers, and suspending functions appear on the system trace, and how to interpret their behavior in real-world applications.

We’ll dive into how Kotlin constructs translate to threads, tasks, and context switches at runtime, revealing common bottlenecks like dispatcher overloads or nested coroutine hierarchies. Along the way, we’ll discuss techniques to instrument your own traces, correlate them with Kotlin runtime states, and visualize structured concurrency in action.

By the end, you’ll not only understand what your Kotlin code is really doing on the CPU — you’ll have practical strategies for profiling, debugging, and optimizing coroutines in production Android apps.