LWN has an excellent article up on the “latency-criticality aware virtual deadline” (LAVD) scheduler, from a talk at the Linux Plumbers Conference in December.
In particular, I appreciate the detailed discussion of using different profilers and performance-analysis tools at different levels to determine how to optimize scheduling to improve two key goals: providing high average FPS while keeping 99th-percentile FPS as low as possible, e.g. to prevent UI stuttering. Optimizing for battery usage is also important, as the Steam Deck was one of the main targets for this work.
The key finding that came out of his analysis is perhaps somewhat obvious: a single high-level action, such as moving a character on-screen and emitting a sound based on a key-press event, requires that many tasks work together. Some of the tasks are threads in the game process, but others are not because they are in the game engine, kernel, and device drivers; there are often 20 or 30 tasks in a chain that all need to collaborate. Finding tasks with a high waker or wakee frequency and prioritizing them is the basis of the LAVD scheduling policy.
As always with LWN there’s good coverage not only of the talk itself, but also the Q&A following the session and ideas from the audience on tooling and other improvements.
Phoronix also covered a different talk from the same conference (I think) on how Meta is using the LAVD scheduler as the basis for a new default scheduler used on their fleet.
I haven’t had a chance to watch this talk yet (video linked from the article) but I’m very interested in the idea that the same concepts might be useful to a hyper scaler as well as a device like a Steam Deck.