Messages in this thread | | | Date | Tue, 2 Feb 1999 16:39:50 +0100 (CET) | From | Andrea Arcangeli <> | Subject | Re: [patch] killed tqueue_lock spinlock |
| |
On Tue, 2 Feb 1999, Patrik Rak wrote:
> > Using a bit in the bh->sync will allow SMP to scale very better. And we > > Hmm, it was just short-term spinlock, I don't think there is much > real contention.
Agreed but there could be in the future. This will allow to scale better in SMP without harming performances I think.
> > Here the latest update: > > And what about this (maybe I got the memory barriers wrong, it's just to > show the idea):
I can't see a big difference. I still like more my version just because I like to play with the lock with sure atomic operations in task_queue() while run_task_queue() is spinning on the lock. And theorically some really nowadays-crazy architecture may want to have 1 byte data at address -1 (really unlikely to happen I know ;).
Andrea Arcangeli
- 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/
| |