Re: [Patch 17/23] mask v2 = [6/7] nodemask_t_ia64_changes

[Nick Piggin]

Paul Jackson wrote:
> Several architectures have this large version of find_next_bit() code.
>
> It may well make sense for the O(1) scheduler to be inlining this.

No, the schedule() fastpath doesn't use find_next_bit. That is
only used to traverse the runqueues when moving tasks from one
to another. No problem uninlining it there.

If the function is more than a cacheline or two big, you'll
probably get better performance through better cache utilisation
anyway, and you'll be able to use a slightly larger, faster
version if you have one, which is probably a good thing.

Unless there is something specific that I'm not aware of?
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/