Messages in this thread | | | Date | Sun, 2 Feb 2014 22:35:48 -0500 | From | Jörn Engel <> | Subject | Re: [PATCH,RFC] random: collect cpu randomness |
| |
On Sun, 2 February 2014 20:39:22 -0500, Theodore Ts'o wrote: > > The real question is how much overhead does it add, and is it worth > it. Jörn, I take it that was the reason for creating an even faster, > but weaker mixing function? Was the existing "fast mix" causing a > measurable overhead, or was this your just being really paranoid about > not adding anything to the various kernel fastpaths?
It was paranoia. And I am still somewhat paranoid and don't trust my benchmark results yet. Maybe on an 1024-CPU Altix with a 100k-thread workload the overhead is too much. Just because I couldn't measure a difference on my wimpy notebook does not mean much.
Jörn
-- One of the painful things about our time is that those who feel certainty are stupid, and those with any imagination and understanding are filled with doubt and indecision. -- Bertrand Russell -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |