Re: PATCH? avoid the unnecessary wakeups in pipe_read()

[Linus Torvalds]

On Sun, 29 Dec 2024 at 05:58, Oleg Nesterov <oleg@xxxxxxxxxx> wrote:
>
> If I read this code correctly, in this case the child will wakeup the parent
> 4095 times for no reason, pipe_writable() == !pipe_pull() will still be true
> until the last read(fd[0], &c, 1) does

Ack, that patch looks sane to me.

Only wake writer if we actually released a pipe slot, and it was full
before we did so.

Makes sense.

                Linus