From: Norbert Preining on
Dear all,

(please CC)

it seems that some of the (?)recent(?) changes have increased the
power consumption of my note book considerably.

First of all, running powertop with normal programs started, but
doing nothing, I am still at 14W while I could go down to 9W before
(but the 9W was with dimmed display).

In the list of top causes for wakeup I have
Top causes for wakeups:
34.2% (185.3) [kernel scheduler] Load balancing tick
23.9% (129.6) [extra timer interrupt]
10.8% ( 58.6) firefox-bin
9.2% ( 49.7) [iwlagn] <interrupt>
7.2% ( 39.1) [kernel core] hrtimer_start (tick_sched_timer)
3.9% ( 20.9) PS/2 keyboard/mouse/touchpad interrupt
which show one new thing to me I haven't seen before, the Loa balancing tick.

Furthermore, I also had the feeling that while being suspend to RAM
the battery is also emptied faster then before, but by now I have not
concise data points for that.

I am running the latest kernel pulled from git.kernel.org, linux-2.6.

I have seen some patches from Venkatesh Pallipadi dealing twith this
issue (http://lkml.org/lkml/2010/6/9/109) but it does not apply to
the current kernel sources at all.

Please let me know if you have any suggestions of if I should test
something.

Thanks and all the best

Norbert

Please CC
------------------------------------------------------------------------
Norbert Preining preining@{jaist.ac.jp, logic.at, debian.org}
JAIST, Japan TeX Live & Debian Developer
DSA: 0x09C5B094 fp: 14DF 2E6C 0307 BE6D AD76 A9C0 D2BF 4AA3 09C5 B094
------------------------------------------------------------------------
HARBOTTLE (n.)
A particular kind of fly which lives inside double glazing.
--- Douglas Adams, The Meaning of Liff
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Peter Zijlstra on
On Wed, 2010-07-07 at 01:45 +0900, Norbert Preining wrote:

> it seems that some of the (?)recent(?) changes have increased the
> power consumption of my note book considerably.
>
> First of all, running powertop with normal programs started, but
> doing nothing, I am still at 14W while I could go down to 9W before
> (but the 9W was with dimmed display).
>
> In the list of top causes for wakeup I have
> Top causes for wakeups:
> 34.2% (185.3) [kernel scheduler] Load balancing tick
> 23.9% (129.6) [extra timer interrupt]
> 10.8% ( 58.6) firefox-bin
> 9.2% ( 49.7) [iwlagn] <interrupt>
> 7.2% ( 39.1) [kernel core] hrtimer_start (tick_sched_timer)
> 3.9% ( 20.9) PS/2 keyboard/mouse/touchpad interrupt
> which show one new thing to me I haven't seen before, the Loa balancing tick.

I think that is what powertop calls our regular tick (Arjan?), and as
long as you're not idle nohz can't kick in, I'd be looking at what keeps
nohz from happening,.. those extra timer interrupts could be
responsible..

> Furthermore, I also had the feeling that while being suspend to RAM
> the battery is also emptied faster then before, but by now I have not
> concise data points for that.
>
> I am running the latest kernel pulled from git.kernel.org, linux-2.6.

Right, I'm quite puzzled by that, looking through the result of:
git log v2.6.34..origin/master kernel/sched*

Nothing really shouts me, me, me :-)

You could try and look at:

99bd5e2f245d8 (sched: Fix select_idle_sibling() logic in select_task_rq_fair())
3c93717cfa513 (sched: Fix over-scheduling bug)

And that latter only if you actually have group scheduling enabled.

Other than that, I'm afraid I'll have to ask you to bisect this.

> I have seen some patches from Venkatesh Pallipadi dealing twith this
> issue (http://lkml.org/lkml/2010/6/9/109) but it does not apply to
> the current kernel sources at all.

Those patches are merged and waiting for the .36 merge window, try a
-tip kernel
(git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git) if
you want to give them a go.


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Peter Zijlstra on
On Thu, 2010-07-08 at 04:57 -0700, Arjan van de Ven wrote:
> On Thu, 08 Jul 2010 11:06:32 +0200
> Peter Zijlstra <peterz(a)infradead.org> wrote:
>
> > On Wed, 2010-07-07 at 01:45 +0900, Norbert Preining wrote:
> >
> > > it seems that some of the (?)recent(?) changes have increased the
> > > power consumption of my note book considerably.
> > >
> > > First of all, running powertop with normal programs started, but
> > > doing nothing, I am still at 14W while I could go down to 9W before
> > > (but the 9W was with dimmed display).
> > >
> > > In the list of top causes for wakeup I have
> > > Top causes for wakeups:
> > > 34.2% (185.3) [kernel scheduler] Load balancing tick
> > > 23.9% (129.6) [extra timer interrupt]
> > > 10.8% ( 58.6) firefox-bin
> > > 9.2% ( 49.7) [iwlagn] <interrupt>
> > > 7.2% ( 39.1) [kernel core] hrtimer_start (tick_sched_timer)
> > > 3.9% ( 20.9) PS/2 keyboard/mouse/touchpad interrupt
> > > which show one new thing to me I haven't seen before, the Loa
> > > balancing tick.
> >
> > I think that is what powertop calls our regular tick (Arjan?), and as
>
> it's "hrtimer_start_range_ns (tick_sched_timer)" if it's done by the
> idle thread.
>

then wth is "[kernel scheduler] load balancing tick"?
and for that matter, what is "[extra timer interrupt]", surely the timer
hardware doesn't generate spurious interrupts?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Arjan van de Ven on
On Thu, 08 Jul 2010 11:06:32 +0200
Peter Zijlstra <peterz(a)infradead.org> wrote:

> On Wed, 2010-07-07 at 01:45 +0900, Norbert Preining wrote:
>
> > it seems that some of the (?)recent(?) changes have increased the
> > power consumption of my note book considerably.
> >
> > First of all, running powertop with normal programs started, but
> > doing nothing, I am still at 14W while I could go down to 9W before
> > (but the 9W was with dimmed display).
> >
> > In the list of top causes for wakeup I have
> > Top causes for wakeups:
> > 34.2% (185.3) [kernel scheduler] Load balancing tick
> > 23.9% (129.6) [extra timer interrupt]
> > 10.8% ( 58.6) firefox-bin
> > 9.2% ( 49.7) [iwlagn] <interrupt>
> > 7.2% ( 39.1) [kernel core] hrtimer_start (tick_sched_timer)
> > 3.9% ( 20.9) PS/2 keyboard/mouse/touchpad interrupt
> > which show one new thing to me I haven't seen before, the Loa
> > balancing tick.
>
> I think that is what powertop calls our regular tick (Arjan?), and as

it's "hrtimer_start_range_ns (tick_sched_timer)" if it's done by the
idle thread.


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Norbert Preining on
On Do, 08 Jul 2010, Peter Zijlstra wrote:
> then wth is "[kernel scheduler] load balancing tick"?
> and for that matter, what is "[extra timer interrupt]", surely the timer
> hardware doesn't generate spurious interrupts?

Just one more point, searching a bit more in the net I found the following
patch (forgot who wrote it) which I merged into my current git:
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a878b53..f26efba 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3248,6 +3248,9 @@ int select_nohz_load_balancer(int stop_tick)
if (stop_tick) {
cpu_rq(cpu)->in_nohz_recently = 1;

+ if (!mc_capable())
+ return 0;
+
if (!cpu_active(cpu)) {
if (atomic_read(&nohz.load_balancer) != cpu)
return 0;
@@ -3297,6 +3300,9 @@ int select_nohz_load_balancer(int stop_tick)
if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
return 0;

+ if (!mc_capable())
+ return 0;
+
cpumask_clear_cpu(cpu, nohz.cpu_mask);

if (atomic_read(&nohz.load_balancer) == cpu)

Now the output looks like:
Cn Avg residency P-states (frequencies)
C0 (cpu running) ( 2.7%) Turbo Mode 0.2%
C0 0.0ms ( 0.0%) 2.54 Ghz 0.0%
C1 mwait 0.8ms ( 0.0%) 1.60 Ghz 0.0%
C2 mwait 0.4ms ( 1.4%) 800 Mhz 99.8%
C6 mwait 4.9ms (95.9%)

Wakeups-from-idle per second : 228.4 interval: 10.0s
Power usage (ACPI estimate): 11.7W (7.3 hours)

Top causes for wakeups:
22.4% ( 55.4) [kernel scheduler] Load balancing tick
16.6% ( 41.2) [iwlagn] <interrupt>
16.0% ( 39.7) [extra timer interrupt]
15.2% ( 37.7) [kernel core] hrtimer_start (tick_sched_timer)
13.7% ( 33.9) firefox-bin
2.4% ( 5.9) [ahci] <interrupt>
2.0% ( 5.0) syndaemon


which looks better

Best wishes

Norbert
------------------------------------------------------------------------
Norbert Preining preining@{jaist.ac.jp, logic.at, debian.org}
JAIST, Japan TeX Live & Debian Developer
DSA: 0x09C5B094 fp: 14DF 2E6C 0307 BE6D AD76 A9C0 D2BF 4AA3 09C5 B094
------------------------------------------------------------------------
OSWALDTWISTLE (n. Old Norse)
Small brass wind instrument used for summoning Vikings to lunch when
they're off on their longships, playing.
--- Douglas Adams, The Meaning of Liff
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/