On Thu, May 26, 2011 at 11:37 AM, Claudio Freire <klaussfreire@gmail.com> wrote:
> On Thu, May 26, 2011 at 6:02 PM, Merlin Moncure <mmoncure@gmail.com> wrote:
>> The point is what we can prove, because going through the
>> motions of doing that is useful.
>
> Exactly, and whatever you can "prove" will be workload-dependant.
> So you can't prove anything "generally", since no single setting is
> best for all.
Then we should stop telling people to adjust it unless we can match
the workload to the improvement. There are some people here who can
do that as if by magic, but that's not the issue. I'm trying to
understand the why it works better for some than for others. What's
frustrating is simply believing something is the case, without trying
to understand why. How about, instead of arguing with me, coming up
with something for the challenge?
merlin