Messages in this thread | | | From | (Davide Libenzi) | Subject | Re: [patch] new spinlock variant, spinlock-2.3.30-A4 | Date | Tue, 30 Nov 1999 23:55:30 +0100 |
| |
Tuesday, November 30, 1999 10:50 PM Ingo Molnar <mingo@chiara.csoma.elte.hu> wrote :
> yes, true. Keep in mind that this only affects the slow path. The above > spinlock would be implemented as a function anyway (we do not want to > inline it), and in that case the slow path can eg. use queued spinlocks > (spinlock chains through on-stack variables) or exponential backoff, or > whatever technique.
OK, I've misunderstood that the code You suggested was a replacement of the "lock" one while this is only a fast test, failing it CPUs falls executing the "lock" code.
Cheers, Davide.
-- "Debian, the Freedom in Freedom."
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |