Re: [performance bug] volanomark regression on 37-rc1

["Alex,Shi" <alex.shi@intel.com>]

On Tue, 2010-11-16 at 22:38 +0800, Rakib Mullick wrote:
> On 11/16/10, Alex,Shi <alex.shi@intel.com> wrote:
> > When do performance testing on 37-rc1 kernel on Core2 machines, we find
> > the volanomark loopback performance drop about 30%, that due to
> > commit:fab476228ba37907ad7
> >
> Was that test was made before and after applying above commit? Would
> love to know, how did you find that commit (I mean was it a git
> bisection)?
Yes, git bisect found this commit. 

> >
> > It seems some of load_balance() is not necessary that caused by avg_idle
> > setting. But do not know more details of the volano running. Anyone like
> > to give a comments for this issue?
> >
> Does VolanoMark is used for scheduler benchmarking? If I'm not wrong,
> I don't think it directly relates to scheduler benchmarking.
Yes, but lots of benchmarks often find other part kernel issues. like
hackbench/netperf often find VM performance issues. And an our cache
testing tool often find scheduler problem. 
> 
> > Ncrao, I have no idea of your benchmarks, but just guess removing the
> > avg_idle setting won't bring much wakeup delay for tasks. Could you like
> > to show some data of this?
> >
> > The vmstat output for .36 and .37-rc1 kernel as below:
> 
> You are showing the output of .36 and .37-rc1. If Ncrao's commit is
> guilty for this performance regression, then what are the results of
> before and after applied Ncrao's commit. Then, what are the result
> after applying your patch. You are showing vmstat output of .36 and
> .37-rc1, which really doesn't prove the point of your patch. It needs
> to be more clearer.
The vmstat for .36 represents original kernel, .37-rc1 represent with
the Ncrao's patch.
> 
> 
> thanks,
> rakib
> 
> 
> > Regards
> > Alex
> >
> > --
> > 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/
> >