Moses is a software engineer at Twitter and is a finagle maintainer. He likes reading.
We choose microservice architectures for many different reasons, including, often, improving reliability. However, there is a dark side. Modular systems have many benefits, but as you add more components, each of which can fail, it makes the overall system more fragile, because there are new ways in which it can fail that previously didn't exist. From its inception, Finagle was designed as a toolkit for reliable systems. We'll discuss understanding the reliability of your system (monitoring! load tests! service level objectives!), how to recover when your system fails (alerts! rollbacks! rolling restarts! failovers!), how to make a system reliable (retries! backpressure! circuit breakers!), and how to debug a reliability problem (tracing! logs! persistence!).