My day job is working on the Arroyo stream processing engine, which executes complex, stateful queries over high-scale streams of events. Computing things like windowed aggregates, stream joins, and incrementally-computed SQL involves, as you might imagine, a lot of sophisticated algorithms and systems. Doing it much faster than existing systems like Apache Flink took careful performance engineering at every level of the stack. But…I'm going to let you in on a little secret. The sad truth of thi...