Stream processors are used for many things, including computations, creating derived streams, and taking actions based on streaming data. But one other common use case is keeping databases up to date. This presents a number of challenges, including how to load balance, how to avoid duplicating data and dropping data, and how to handle backfills. We'll talk about some of the possible approaches, their pros and cons, and look at how they are used in real world systems like Kafka, Storm, Samza, Druid, and others.