>If you increase it above +1 bad things happen and tasks get starved unfairly
>at least from testing with 2.1.x before 2.2. I dont think anything has changd
I didn't noticed anything of obviously bad here so far. Even in 2.2.x
(without the active_mm information) such heuristic was going to do the
wrong thing and maybe to advantage way too much threads against other
tasks. IMHO with the reliable active_mm information we have in 2.3.x (so
being sure to do the right thing) using a +5 should not hurt (maybe we
could remove 4 points from the per-processor penality?).
It's a per-ARCH define so everybody can test the stuff on each arch and
tune it to give us the best number :).
Andrea
-
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/