On Sat, Aug 6, 2011 at 11:51 PM, Al Viro <viro@xxxxxxxxxxxxxxxxxx> wrote:
>
> Trivial nit: s/do_follow_link/should_follow_link/, I think...
Done. I've also done more performance testing, and it seems that now
it would be a win again to do the "prefetch inode" in
__d_lookup_rcu().
But I'll leave it be for now. My test loads are ridiculously
pathname-intensive, I don't know if anything else really cares that
deeply.
At least there is no longer anything in the profiles that look
horribly stupid (except for the security subsystem - pointer chasing
through i_security, and I can't see anything we can do about that).
Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
