Ingo Molnar wrote:
quoted text
> * Gregory Haskins <ghaskins@novell.com> wrote:
>
>  =20
>>>> Speaking of this: Another patch I submitted to you Ingo (had to do=20
>>>> with updating the load_weight inside task_setprio) seems to also=20
>>>> have this phenomenon: e.g. its technically correct but further=20
>>>> testing has revealed negative repercussions elsewhere.  So please=20
>>>> ignore that patch (or revert if you already pulled in, but I don't=20
>>>> think you have).  Ill try to look into this issue as well.
>>>>        =20
>>> ok, under which thread/subject is that? Not queued in tip/sched/*=20
>>> yet, correct?
>>>  =20
>>>      =20
>> Here is the original thread:
>>
>> http://lkml.org/lkml/2008/7/3/416
>>
>> I do not believe you have queued it anywhere (public anyway) yet.
>>
>> Note I have already invalidated 1/2, and now I am retracting 2/2 as=20
>> well.  (1/2 is actually a bogus patch, 2/2 is "technically correct"=20
>> but causes ripples in the load balancer that need to be sorted out=20
>> first.
>>    =20
>
> ok, thanks. I'm curious, what are those ripple effects? Stability or=20
> performance?
>  =20

Performance.  I found it while working on my pi series (which fyi I=20
should have a v2 refresh for soon, probably today...i am hoping to get=20
some review feedback from you on that as well, time permitting of course =
;).

Basically the behavior I was observing was that kernel builds via distcc =

would cluster all the cc1 jobs on a single core.  At first I thought my=20
pi-series was screwed up, but then I realized I had applied the patch=20
referenced above earlier in my development tree, and removing it allowed =

pi to work fine.

I found the problem with in once boot cycle with ftrace (thanks=20
Steve!).  Basically newidle balancing was always returning "no=20
imbalance" even though I had 32 cc1 threads on 1 core, and 3 idle=20
cores.  Clearly not correct!  So I think that by adjusting the load up,=20
we throw off the hysteresis built into the load averages and cause the=20
system to incorrectly think it's balanced. TBD.

-Greg


quoted text
> 	Ingo
>  =20