Rethinking the futex API
Rethinking the futex API
Posted Jun 24, 2020 19:17 UTC (Wed) by itsmycpu (guest, #139639)In reply to: Rethinking the futex API by rweikusat2
Parent article: Rethinking the futex API
> That's an insanely complicated way to transfer a linked list from a head pointer a in the kernel to another head pointer b in the kernel. It's much simpler if the kernel just wakes one thread and transfers the existing list to the other futex.
I'm not sure if you are discussing a more specific question, but just to point it out, for example a user space implementation of the producer/consumer model can (if so designed) just move a waiting entry from one producer's list to another producer's list without any wake ups or even kernel calls. (Except a wake call in the case one is ready.)
