Hi Eero,
On Mon, 2018-07-30 at 11:33 +0300, Eero Tamminen wrote:
> Hi,
>
> On 28.07.2018 17:14, Srinivas Pandruvada wrote:
> > On Fri, 2018-07-27 at 22:34 -0700, Francisco Jerez wrote:
> > > Srinivas Pandruvada <srinivas.pandruv...@linux.intel.com> writes:
> > >
> > > > Enable HWP boost on Skylake server and workstations.
> > > >
> > >
> > > Please revert this series, it led to significant energy usage and
> > > graphics performance regressions [1].
> >
> > Which SKX platform is targeted to graphics?
>
> Patch that Chris pointed out is this:
> +static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
> + ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
> + ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_funcs),
> + {}
> +};
>
> The regressing platforms in our test system were:
> - SKL 6600K i5 / GT2
> - SKL 6770HQ i7 / GT4e
>
> SKL-U i5 / GT3e device wasn't impacted, so I assume U devices don't
> match INTEL_FAM6_SKYLAKE_DESKTOP.
I have updated some steps in the bugzilla. Can you try that?
Also add one workload which will show this issue immediately including
any parameters you need to add.
Thanks,
Srinivas
>
>
>
> - Eero
>
> > > The reasons are roughly the ones
> > > we discussed by e-mail off-list last April: This causes the
> > > intel_pstate
> > > driver to decrease the EPP to zero
> >
> > No. You didn't check this series. We are not using EPP at all.
> > The boost mechanism used here is not boost to max.
> >
> > Thanks,
> > Srinivas
> >
> > > when the workload blocks on IO
> > > frequently enough, which for the regressing benchmarks detailed
> > > in
> > > [1]
> > > is a symptom of the workload being heavily IO-bound, which means
> > > they
> > > won't benefit at all from the EPP boost since they aren't
> > > significantly
> > > CPU-bound, and they will suffer a decrease in parallelism due to
> > > the
> > > active CPU core using a larger fraction of the TDP in order to
> > > achieve
> > > the same work, causing the GPU to have a lower power budget
> > > available,
> > > leading to a decrease in system performance.
> > >
> > > You may want to give a shot to my previous suggestion of using
> > > [2] in
> > > order to detect whether the system is IO-bound, which you can use
> > > as
> > > an
> > > indicator that the optimization implemented in this series cannot
> > > possibly improve performance and can be expected to hurt energy
> > > usage.
> > >
> > > Thanks.
> > >
> > > [1] https://bugs.freedesktop.org/show_bug.cgi?id=107410
> > > [2] https://patchwork.kernel.org/patch/10312259/
> > >
> > > > Reported-by: Mel Gorman <mgor...@techsingularity.net>
> > > > Tested-by: Giovanni Gherdovich <ggherdov...@suse.cz>
> > > > Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.i
> > > > ntel
> > > > .com>
> > > > ---
> > > > drivers/cpufreq/intel_pstate.c | 10 ++++++++++
> > > > 1 file changed, 10 insertions(+)
> > > >
> > > > diff --git a/drivers/cpufreq/intel_pstate.c
> > > > b/drivers/cpufreq/intel_pstate.c
> > > > index 70bf63bb4e0e..01c8da1f99db 100644
> > > > --- a/drivers/cpufreq/intel_pstate.c
> > > > +++ b/drivers/cpufreq/intel_pstate.c
> > > > @@ -1794,6 +1794,12 @@ static const struct x86_cpu_id
> > > > intel_pstate_cpu_ee_disable_ids[] = {
> > > > {}
> > > > };
> > > >
> > > > +static const struct x86_cpu_id intel_pstate_hwp_boost_ids[]
> > > > __initconst = {
> > > > + ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
> > > > + ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_funcs),
> > > > + {}
> > > > +};
> > > > +
> > > > static int intel_pstate_init_cpu(unsigned int cpunum)
> > > > {
> > > > struct cpudata *cpu;
> > > > @@ -1824,6 +1830,10 @@ static int
> > > > intel_pstate_init_cpu(unsigned
> > > > int cpunum)
> > > > intel_pstate_disable_ee(cpunum);
> > > >
> > > > intel_pstate_hwp_enable(cpu);
> > > > +
> > > > + id =
> > > > x86_match_cpu(intel_pstate_hwp_boost_ids);
> > > > + if (id)
> > > > + hwp_boost = true;
> > > > }
> > > >
> > > > intel_pstate_get_cpu_pstates(cpu);
> > > > --
> > > > 2.13.6
>
>
