Re: [Bug #11207] VolanoMark regression with 2.6.27-rc1

From: Zhang, Yanmin
Date: Tue Oct 07 2008 - 22:37:11 EST



On Tue, 2008-10-07 at 17:48 +0200, Peter Zijlstra wrote:
> On Wed, 2008-10-08 at 02:11 +1100, Nick Piggin wrote:
> > On Sunday 05 October 2008 04:28, Rafael J. Wysocki wrote:
> > > This message has been generated automatically as a part of a report
> > > of recent regressions.
> > >
> > > The following bug entry is on the current list of known regressions
> > > from 2.6.26. Please verify if it still should be listed and let me know
> > > (either way).
> > >
> > >
> > > Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=11207
> > > Subject : VolanoMark regression with 2.6.27-rc1
> > > Submitter : Zhang, Yanmin <yanmin_zhang@xxxxxxxxxxxxxxx>
> > > Date : 2008-07-31 3:20 (66 days old)
> > > References : http://marc.info/?l=linux-kernel&m=121747464114335&w=4
> > > Handled-By : Zhang, Yanmin <yanmin_zhang@xxxxxxxxxxxxxxx>
> > > Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> > > Dhaval Giani <dhaval@xxxxxxxxxxxxxxxxxx>
> > > Miao Xie <miaox@xxxxxxxxxxxxxx>
> >
> > Curious: what's happening with this one, handlers? Any progress being made?
>
> Sadly not much, I can't seem to reproduce :-(
The regression is bigger with more cpu.

>
> Yanmin, does the wakeup patch I did for oltp help this workload any?
>
> http://marc.info/?l=linux-kernel&m=122194673932703&w=4
I tested it against 2.6.29-rc9 on 8-core stoakley and 16-core tigerton. volanoMark
chatroom number is default 10.
Basically, comparing with pure 2.6.27-rc9, the patched kernel's result has about 2%
regression. Group scheduling is enabled.

-yanmin


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/