Messages in this thread | | | Date | Sun, 1 Dec 2013 10:58:25 -0800 | Subject | Re: [RFC patch 0/5] futex: Allow lockless empty check of hashbucket plist in futex_wake() | From | Linus Torvalds <> |
| |
On Sun, Dec 1, 2013 at 8:55 AM, Ingo Molnar <mingo@kernel.org> wrote: > > Keeping the page invariant would bring significant performance > advantages to hashing.
Or not. Rather, it would make things much worse. The virtual address is much simpler and better to avoid needing any page table lookup etc crap. The key is just the mm and the virtual address, and no silly page table walks etc necessary.
Of course, I have no idea if people are properly using the private futexes. glibc _should_ use them, but who the heck knows..
Linus
| |