Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1502618 > unrolled thread

4.8.1 regression with cpufreq governors

Started byTim Walberg <twalberg@comcast.net>
First post2016-10-18 03:00 +0200
Last post2016-10-20 05:30 +0200
Articles 5 — 3 participants

Back to article view | Back to linux.kernel


Contents

  4.8.1 regression with cpufreq governors Tim Walberg <twalberg@comcast.net> - 2016-10-18 03:00 +0200
    Re: 4.8.1 regression with cpufreq governors "Rafael J. Wysocki" <rjw@rjwysocki.net> - 2016-10-18 23:10 +0200
      Re: 4.8.1 regression with cpufreq governors Viresh Kumar <viresh.kumar@linaro.org> - 2016-10-19 16:20 +0200
      Re: 4.8.1 regression with cpufreq governors Tim Walberg <twalberg@comcast.net> - 2016-10-19 22:10 +0200
        Re: 4.8.1 regression with cpufreq governors Viresh Kumar <viresh.kumar@linaro.org> - 2016-10-20 05:30 +0200

#1502618 — 4.8.1 regression with cpufreq governors

FromTim Walberg <twalberg@comcast.net>
Date2016-10-18 03:00 +0200
Subject4.8.1 regression with cpufreq governors
Message-ID<stqV3-2Vn-1@gated-at.bofh.it>
May or may not be related to similar reports, but here's what I've just observed
on my system. Built a stock kernel from tags/v4.8.1, relevant cpufreq bits:

CONFIG_ACPI_CPU_FREQ_PSS=y
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_GOV_ATTR_SET=y
CONFIG_CPU_FREQ_GOV_COMMON=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_FREQ_STAT_DETAILS=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_ONDEMAND=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
# CONFIG_X86_PCC_CPUFREQ is not set
CONFIG_X86_ACPI_CPUFREQ=m
CONFIG_X86_ACPI_CPUFREQ_CPB=y


Conservative is set as default governer, yet when boot completes, all CPUs are
pegged at the highest frequency. Changing governor to powersave knocks them all
down to the lowest available frequency. Putting them back on conservative (or
ondemand) results in no change in frequency, despite generating load. Switching
to performance of course kicks them back up to high frequency. Basically, the
governors don't seem to be ... governing.

-- 
twalberg@gmail.com, twalberg@comcast.net

[toc] | [next] | [standalone]


#1503361

From"Rafael J. Wysocki" <rjw@rjwysocki.net>
Date2016-10-18 23:10 +0200
Message-ID<stJO3-7sS-45@gated-at.bofh.it>
In reply to#1502618
On Monday, October 17, 2016 07:46:06 PM Tim Walberg wrote:
> May or may not be related to similar reports, but here's what I've just observed
> on my system. Built a stock kernel from tags/v4.8.1, relevant cpufreq bits:
> 
> CONFIG_ACPI_CPU_FREQ_PSS=y
> CONFIG_CPU_FREQ=y
> CONFIG_CPU_FREQ_GOV_ATTR_SET=y
> CONFIG_CPU_FREQ_GOV_COMMON=y
> CONFIG_CPU_FREQ_STAT=y
> CONFIG_CPU_FREQ_STAT_DETAILS=y
> # CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
> # CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
> # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
> # CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
> CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE=y
> # CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set
> CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
> CONFIG_CPU_FREQ_GOV_POWERSAVE=m
> CONFIG_CPU_FREQ_GOV_USERSPACE=m
> CONFIG_CPU_FREQ_GOV_ONDEMAND=m
> CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
> CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
> # CONFIG_X86_PCC_CPUFREQ is not set
> CONFIG_X86_ACPI_CPUFREQ=m
> CONFIG_X86_ACPI_CPUFREQ_CPB=y
> 
> 
> Conservative is set as default governer, yet when boot completes, all CPUs are
> pegged at the highest frequency. Changing governor to powersave knocks them all
> down to the lowest available frequency. Putting them back on conservative (or
> ondemand) results in no change in frequency, despite generating load. Switching
> to performance of course kicks them back up to high frequency. Basically, the
> governors don't seem to be ... governing.

The "convervative" governor issue seems to be the one fixed recently
(http://git.kernel.org/cgit/linux/kernel/git/rafael/linux-pm.git/commit/?h=pm-cpufreq&id=abb6627910a1e783c8e034b35b7c80e5e7f98f41).

I'm not sure why "ondemand" behaves incorrectly for you though.

Thanks,
Rafael

[toc] | [prev] | [next] | [standalone]


#1503637

FromViresh Kumar <viresh.kumar@linaro.org>
Date2016-10-19 16:20 +0200
Message-ID<stZSQ-2nd-133@gated-at.bofh.it>
In reply to#1503361
On 18-10-16, 23:10, Rafael J. Wysocki wrote:
> On Monday, October 17, 2016 07:46:06 PM Tim Walberg wrote:
> > May or may not be related to similar reports, but here's what I've just observed
> > on my system. Built a stock kernel from tags/v4.8.1, relevant cpufreq bits:
> > 
> > CONFIG_ACPI_CPU_FREQ_PSS=y
> > CONFIG_CPU_FREQ=y
> > CONFIG_CPU_FREQ_GOV_ATTR_SET=y
> > CONFIG_CPU_FREQ_GOV_COMMON=y
> > CONFIG_CPU_FREQ_STAT=y
> > CONFIG_CPU_FREQ_STAT_DETAILS=y
> > # CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
> > # CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
> > # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
> > # CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
> > CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE=y
> > # CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set
> > CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
> > CONFIG_CPU_FREQ_GOV_POWERSAVE=m
> > CONFIG_CPU_FREQ_GOV_USERSPACE=m
> > CONFIG_CPU_FREQ_GOV_ONDEMAND=m
> > CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
> > CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
> > # CONFIG_X86_PCC_CPUFREQ is not set
> > CONFIG_X86_ACPI_CPUFREQ=m
> > CONFIG_X86_ACPI_CPUFREQ_CPB=y
> > 
> > 
> > Conservative is set as default governer, yet when boot completes, all CPUs are
> > pegged at the highest frequency. Changing governor to powersave knocks them all
> > down to the lowest available frequency. Putting them back on conservative (or
> > ondemand) results in no change in frequency, despite generating load. Switching
> > to performance of course kicks them back up to high frequency. Basically, the
> > governors don't seem to be ... governing.
> 
> The "convervative" governor issue seems to be the one fixed recently
> (http://git.kernel.org/cgit/linux/kernel/git/rafael/linux-pm.git/commit/?h=pm-cpufreq&id=abb6627910a1e783c8e034b35b7c80e5e7f98f41).
> 
> I'm not sure why "ondemand" behaves incorrectly for you though.

@Tim: Can you please try this as well:

https://marc.info/?l=linux-kernel&m=147624218132250&w=2

Subject: [PATCH V2] cpufreq: skip invalid entries when searching the frequency

-- 
viresh

[toc] | [prev] | [next] | [standalone]


#1504307

FromTim Walberg <twalberg@comcast.net>
Date2016-10-19 22:10 +0200
Message-ID<su5lv-644-1@gated-at.bofh.it>
In reply to#1503361
This indeed turned out to be the fix.

On 10/18/2016 23:10 +0200, Rafael J. Wysocki wrote:
>>	On Monday, October 17, 2016 07:46:06 PM Tim Walberg wrote:
>>	> May or may not be related to similar reports, but here's what I've just observed
>>	> on my system. Built a stock kernel from tags/v4.8.1, relevant cpufreq bits:
>>	> 
>>	> CONFIG_ACPI_CPU_FREQ_PSS=y
>>	> CONFIG_CPU_FREQ=y
>>	> CONFIG_CPU_FREQ_GOV_ATTR_SET=y
>>	> CONFIG_CPU_FREQ_GOV_COMMON=y
>>	> CONFIG_CPU_FREQ_STAT=y
>>	> CONFIG_CPU_FREQ_STAT_DETAILS=y
>>	> # CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
>>	> # CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
>>	> # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
>>	> # CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
>>	> CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE=y
>>	> # CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set
>>	> CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
>>	> CONFIG_CPU_FREQ_GOV_POWERSAVE=m
>>	> CONFIG_CPU_FREQ_GOV_USERSPACE=m
>>	> CONFIG_CPU_FREQ_GOV_ONDEMAND=m
>>	> CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
>>	> CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
>>	> # CONFIG_X86_PCC_CPUFREQ is not set
>>	> CONFIG_X86_ACPI_CPUFREQ=m
>>	> CONFIG_X86_ACPI_CPUFREQ_CPB=y
>>	> 
>>	> 
>>	> Conservative is set as default governer, yet when boot completes, all CPUs are
>>	> pegged at the highest frequency. Changing governor to powersave knocks them all
>>	> down to the lowest available frequency. Putting them back on conservative (or
>>	> ondemand) results in no change in frequency, despite generating load. Switching
>>	> to performance of course kicks them back up to high frequency. Basically, the
>>	> governors don't seem to be ... governing.
>>	
>>	The "convervative" governor issue seems to be the one fixed recently
>>	(http://git.kernel.org/cgit/linux/kernel/git/rafael/linux-pm.git/commit/?h=pm-cpufreq&id=abb6627910a1e783c8e034b35b7c80e5e7f98f41).
>>	
>>	I'm not sure why "ondemand" behaves incorrectly for you though.
>>	
>>	Thanks,
>>	Rafael
End of included message



-- 
twalberg@gmail.com, twalberg@comcast.net

[toc] | [prev] | [next] | [standalone]


#1504488

FromViresh Kumar <viresh.kumar@linaro.org>
Date2016-10-20 05:30 +0200
Message-ID<sucdj-1YK-5@gated-at.bofh.it>
In reply to#1504307
On 19-10-16, 15:06, Tim Walberg wrote:
> This indeed turned out to be the fix.

Really? How can this fix the ondemand governor thing?

Or is it that Ondemand never broke ?

-- 
viresh

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web