This is the mail archive of the
mailing list for the glibc project.
Re: [PATCH 02/10] Add the low level infrastructure for pthreads lockelision with TSX
On 01/11/2013 06:06 PM, Andi Kleen wrote:
> Also I actually disagree that exposing tunables is a bad thing.
> The current glibc strategy of hardcoding dubious magic numbers from 10+
> years ago (like it is done for the adaptive lock) is a poor one, and contrary
> to any good continuous performance improvement strategy.
> Of course most users will not tune, but the few that do can give you
> priceless feedback and they need to have appropiate mechanisms.
I fully agree that hardcoded magic numbers were just a terrible idea.
We need a framework and policy for tunables.
I'll try to work something up and send it out to the list for discussion.
At present we're already starting to look at more tunables for pthread
stack sizes, libm trade-offs, and now HLE. Things are getting messy.
Again, this is totally not your fault Andi, you've just touched a sore
spot where the *community* needs to do some work.