Without the Futex, It's Futile

Summary

Phil Eaton’s book club is starting The Art of Multiprocessor Programming, 2nd Edition , which is a very well regarded textbook, and pretty recently updated (2021). I’ve even heard of a couple of authors.I’ve done a lot of concurrent programming, and have always felt like I’ve still got plenty to learn, so I was excited for the topic. So far, what I’ve learned is that I would never recommend this book, despite any merits.Academia certainly struggles to find the right balance between teaching foundational principles and practical information. Being this book is explicitly targeting fourth-year undergraduates and grad students, it should definitely cover the fundamentals, right?So how the heck could it not cover the futex??Isn’t that just a type of mutex? Surely the futex can’t be THAT important?The name sure sounds like “mutex”, and that is where the name comes from: “fast, user space mutex”. But, it isn’t really, it’s a building block for concurrency primitives that ushered in a modern world of concurrent performance that makes System V (sysv) feel so old and busted, it feels wrong to even call it a dinosaur 🦖, as if it were once mighty?Way back in the last millennium, locking primitives were pretty much all based on the System V IPC (inter-process communication) code, specifically their semaphore code. All common concurrency primitives were over-complicated under the hood, and just didn’t scale well to large numbers of threads.Until Linux added the futex.Going back to the original futuex paper in 2002, it was immediately clear that the futex was a huge improvement in highly concurrent environments. Just in that original paper, their tests with 1000 parallel tasks ran 20-120 times faster than sysv locks..🤯Needless to say, other common operating systems followed suit, including Windows in 2012 and macOS by 2016.These days, any good locking primitive is going to be based on a futex. You should expect system libraries like pthreads will use the futex extensively.Wait, a...