Messages in this thread | | | Date | Mon, 1 Jul 2013 12:19:49 -0700 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH RFC nohz_full 0/7] v2 Provide infrastructure for full-system idle |
| |
On Mon, Jul 01, 2013 at 06:19:10PM +0200, Andi Kleen wrote: > > I am guessing that you want CONFIG_NO_HZ_FULL to implicitly enable > > the sysidle code so that CONFIG_NO_HZ_FULL_SYSIDLE can be eliminated. > > I will be happy to take that step, but only after I gain full confidence > > in the correctness and performance of the sysidle code. > > FWIW if you want useful testing you need to enable it by default > (as part of NO_IDLE_HZ) anyways. Users will most likely pick > whatever is "default" in Kconfig.
At this point in the process, I want testers who choose to test. Hapless victim testers come later. Well, other than randconfig testers, but I consider them to be voluntary hapless victims. ;-)
> > > If you want a switch for testing I would advise a sysctl or sysfs knob > > > > This would work well for the correctness part, but not for the performance > > part. > > What performance part? > > Are you saying this adds so many checks to hot paths that normal runtime > if() with a flag is too expensive?
I am saying that I don't know, and that I want to make it easy for people to find out by comparing to the base configuration -- and for me to be able to detect this from their .config file.
Thanx, Paul
| |