[Intel-gfx] [PATCH] drm/i915: Enable runtime pm

Thu Nov 16 20:45:26 UTC 2017

Em Qui, 2017-11-16 às 20:24 +0200, David Weinehall escreveu:
> On Wed, Nov 08, 2017 at 04:25:42PM +0200, David Weinehall wrote:
> > On Tue, Nov 07, 2017 at 05:18:21PM +0100, Daniel Vetter wrote:
> > > Now that we have CI, and that pm_rpm fully passes (I guess the
> > > audio
> > > folks have implemented proper runtime pm for snd-hda, hooray, pls
> > > confirm) it's time to enable this again by default.
> > > 
> > > Real goal here is to have 1 configuration only that we fully
> > > support,
> > > instead of tons of different codes with every user/customer
> > > tuning it
> > > differently. And really, power stuff should work by default, and
> > > should be enabled by everywhere where it is save to do so.
> > > 
> > > v2: Completely new commit message, a few years passed since v1
> > > ...
> > > 
> > > Cc: Takashi Iwai <tiwai at suse.de>
> > > Cc: Liam Girdwood <liam.r.girdwood at intel.com>
> > > Cc: "Yang, Libin" <libin.yang at intel.com>
> > > Cc: "Lin, Mengdong" <mengdong.lin at intel.com>
> > > Cc: "Li, Jocelyn" <jocelyn.li at intel.com>
> > > Cc: "Kaskinen, Tanu" <tanu.kaskinen at intel.com>
> > > Cc: "Zanoni, Paulo R" <paulo.r.zanoni at intel.com>
> > > Signed-off-by: Daniel Vetter <daniel.vetter at intel.com>
> > 
> > lgtm,
> > 
> > Reviewed-by: David Weinehall <david.weinehall at linux.intel.com>
> 
> Been testing a bit; test results are a bit discouraging when it comes
> to
> idle power consumption.
> 
> Our nightly test suite logs idle power consumption before running any
> tests, after running all tests, and then finally after running
> powertop --auto-tune.
> 
> The before and after cases are similar with and without patch,
> but not so for the auto-tune case.
> 
> Without this patch, powertop --auto-tune yields a massive improvement
> (on NUC6i5 the power consumption drops with more than a factor of 3),
> while with this patch the power consumption just drops with 10% or
> so.

What happens if you keep the autosuspend delay to 10000?

> 
> Judging by the powertop output it seems as though we're getting a lot
> of
> interrupts from i915.
> 
>  *  *  *   Top 10 Power Consumers   *  *  *
> 
> With patch:
> 
> Usage;Events/s;Category;Description
>   0,5%; 75,1;Interrupt;[124] i915
>   0,3%; 48,4;Process;/usr/lib/xorg/Xorg -core :0 -seat seat0 -auth
> /var/run/lightdm/root/:0 -nolisten tcp vt7 -novtswitch
>   0,1%; 42,8;Timer;hrtimer_wakeup
>   0,0%; 34,9;Timer;tick_sched_timer
>   4,2%;  1,1;kWork;i915_hpd_poll_init_work
>   0,1%; 14,0;Process;python2 /opt/scripts/dut/dutlaunch/launch2.py --
> workspace=/opt/jenkins/workspace/Custom_test --iterations=1
> idlepower_before un
>   0,0%; 13,3;Process;[rcu_preempt]
>   0,8%;  1,7;Process;python /opt/scripts/dut/perf-meter.py --avgskip
> 1 --name perf-meter --infofile /tmp/testname GLBenchmark testfw_app
> synmark2 he
>   0,0%;  3,0;Process;compiz
>   0,7%; 0,11;kWork;output_poll_execute
> 
> Without the patch:
> 
> Usage;Events/s;Category;Description
>   0,0%; 29,1;Timer;tick_sched_timer
>   0,1%; 19,9;Process;python2 /opt/scripts/dut/dutlaunch/launch.py --
> workspace=/opt/jenkins/workspace/Nightly_kernel_test/kernel/151077366
> 5/SKL_6260U
>   0,0%; 13,2;Process;[rcu_preempt]
>   0,8%;  1,6;Process;python /opt/scripts/dut/perf-meter.py --avgskip
> 1 --name perf-meter --infofile /tmp/testname GLBenchmark testfw_app
> synmark2 he
>   0,0%;  2,5;Process;compiz
>   0,0%;  1,5;Process;java -jar slave.jar
>   0,0%;  1,2;Interrupt;[3] net_rx(softirq)
>   0,0%;  1,0;kWork;pci_pme_list_scan
>   0,0%;  0,9;Interrupt;[121] xhci_hcd
>   0,1%;  0,5;Process;perf-meter
> 
> As can be seen the i915 driver doesn't even show up without the
> patch,
> while it's the main culprit with the patch.
> 
> Just to eliminate DMC issues I'm going to do another run, but with
> DMC
> v1.27 instead of v1.26.
> 
> 
> Kind regards, David
> 
> > 
> > > ---
> > >  drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
> > >  1 file changed, 3 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > index 8315499452dc..dc24d008d8d4 100644
> > > --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > @@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct
> > > drm_i915_private *dev_priv)
> > >  	struct pci_dev *pdev = dev_priv->drm.pdev;
> > >  	struct device *kdev = &pdev->dev;
> > >  
> > > -	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
> > > +	pm_runtime_set_autosuspend_delay(kdev, 100);
> > >  	pm_runtime_mark_last_busy(kdev);
> > >  
> > >  	/*
> > > @@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct
> > > drm_i915_private *dev_priv)
> > >  		pm_runtime_use_autosuspend(kdev);
> > >  	}
> > >  
> > > +	pm_runtime_allow(kdev);
> > > +
> > >  	/*
> > >  	 * The core calls the driver load handler with an RPM
> > > reference held.
> > >  	 * We drop that here and will reacquire it during
> > > unloading in
> > > -- 
> > > 2.15.0.rc2
> > > 
> > > _______________________________________________
> > > Intel-gfx mailing list
> > > Intel-gfx at lists.freedesktop.org
> > > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
> > 
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx at lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx