> I see your point, but now that I fixed it, it's still at least a nice
> performance optimization (and the new code is really nicer and very more
> fun ;). And you killed a __cli() in every run_task_queue() at least...
I did not have much time to think about it, but it could at least use
some clean up, otherwise it causes unnecessary overhead on uniprocessor
machines (they don't need the bit1 at all).
If it's really an optimization depends IMHO on how much bhs are on the
queue, as testing bit1 for each of them might actually make things
worse...
Patrik
-
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/