i915 intel_powerclamp consuming 50% cpu kidle_inject

Bug #1640000 reported by Michael Gratton
16
This bug affects 3 people
Affects Status Importance Assigned to Milestone
linux (Ubuntu)
Confirmed
Medium
Unassigned

Bug Description

At least since upgrading to Yakkey, my MacBookPro12,1 (13", 2015) seems to respond to increased system heat using only kidle_inject, and not the built-in fan. kidle_inject with kick in rather quickly, especially with the Australian summer starting to be felt, and will render the system near useless.

Doing some investigation, it appears that no fan is registered as a cooling device:

> mjg@payens:~$ grep . /sys/class/thermal/cooling_device*/type
> /sys/class/thermal/cooling_device0/type:Processor
> /sys/class/thermal/cooling_device1/type:Processor
> /sys/class/thermal/cooling_device2/type:Processor
> /sys/class/thermal/cooling_device3/type:Processor
> /sys/class/thermal/cooling_device4/type:intel_powerclamp

Even though one is picked up by applesmc:

> Nov 08 10:08:56 payens kernel: applesmc: key=670 fan=1 temp=35 index=34 acc=0 lux=2 kbd=1

The fan seems to be physically in good condition, I tested it out using the following:

> root@payens:~# echo 6000 > /sys/devices/platform/applesmc.768/fan1_min

Which started it blowing a lot of warm air out.

ProblemType: Bug
DistroRelease: Ubuntu 16.10
Package: linux-image-generic 4.8.0.26.35
ProcVersionSignature: Ubuntu 4.8.0-26.28-generic 4.8.0
Uname: Linux 4.8.0-26-generic x86_64
ApportVersion: 2.20.3-0ubuntu8
Architecture: amd64
AudioDevicesInUse:
 USER PID ACCESS COMMAND
 /dev/snd/controlC1: mjg 3076 F.... pulseaudio
 /dev/snd/controlC0: mjg 3076 F.... pulseaudio
CurrentDesktop: GNOME
Date: Tue Nov 8 13:36:01 2016
HibernationDevice: RESUME=UUID=bc879a1f-ac27-48ae-82dd-3c81b7307dd0
InstallationDate: Installed on 2015-07-22 (475 days ago)
InstallationMedia: Ubuntu-GNOME 15.04 "Vivid Vervet" - Release amd64 (20150422)
Lsusb:
 Bus 002 Device 001: ID 1d6b:0003 Linux Foundation 3.0 root hub
 Bus 001 Device 003: ID 05ac:0273 Apple, Inc.
 Bus 001 Device 002: ID 05ac:8290 Apple, Inc.
 Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
MachineType: Apple Inc. MacBookPro12,1
ProcFB: 0 inteldrmfb
ProcKernelCmdLine: BOOT_IMAGE=/vmlinuz-4.8.0-26-generic root=/dev/mapper/ubuntu--gnome--vg-root ro quiet splash acpi_backlight=vendor i915.fastboot=1
RelatedPackageVersions:
 linux-restricted-modules-4.8.0-26-generic N/A
 linux-backports-modules-4.8.0-26-generic N/A
 linux-firmware 1.161
SourcePackage: linux
UpgradeStatus: Upgraded to yakkety on 2016-10-05 (33 days ago)
dmi.bios.date: 09/28/2015
dmi.bios.vendor: Apple Inc.
dmi.bios.version: MBP121.88Z.0167.B14.1509281135
dmi.board.name: Mac-E43C1C25D4880AD6
dmi.board.vendor: Apple Inc.
dmi.board.version: MacBookPro12,1
dmi.chassis.type: 9
dmi.chassis.vendor: Apple Inc.
dmi.chassis.version: Mac-E43C1C25D4880AD6
dmi.modalias: dmi:bvnAppleInc.:bvrMBP121.88Z.0167.B14.1509281135:bd09/28/2015:svnAppleInc.:pnMacBookPro12,1:pvr1.0:rvnAppleInc.:rnMac-E43C1C25D4880AD6:rvrMacBookPro12,1:cvnAppleInc.:ct9:cvrMac-E43C1C25D4880AD6:
dmi.product.name: MacBookPro12,1
dmi.product.version: 1.0
dmi.sys.vendor: Apple Inc.

Revision history for this message
Michael Gratton (mjog) wrote :
Revision history for this message
Michael Gratton (mjog) wrote :

Similarly to Bug #1389077, I can disable Intel Powerclamp by `rmmod intel_powerclamp` to prevent kidle_inject from being used, and in this case applesmc (presumably) will start the fan kicking in as the system gets hotter.

However unlike Bug #1389077, when intel_powerclamp is loaded here the fan never seems to get used.

Revision history for this message
Brad Figg (brad-figg) wrote : Status changed to Confirmed

This change was made by a bot.

Changed in linux (Ubuntu):
status: New → Confirmed
Revision history for this message
Joseph Salisbury (jsalisbury) wrote : Re: kidle_inject overly onerous, fans never used on MacBookPro12,1

Did this issue start happening after an update/upgrade? Was there a prior kernel version where you were not having this particular problem?

Would it be possible for you to test the latest upstream kernel? Refer to https://wiki.ubuntu.com/KernelMainlineBuilds . Please test the latest v4.9 kernel[0].

If this bug is fixed in the mainline kernel, please add the following tag 'kernel-fixed-upstream'.

If the mainline kernel does not fix this bug, please add the tag: 'kernel-bug-exists-upstream'.

Once testing of the upstream kernel is complete, please mark this bug as "Confirmed".

Thanks in advance.

[0] http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.9-rc4

Changed in linux (Ubuntu):
importance: Undecided → Medium
tags: added: kernel-da-key
Changed in linux (Ubuntu):
status: Confirmed → Incomplete
Revision history for this message
Richard (ismail-a) wrote :

I have it both on a MacBook Air 2011 11" and a MacBook Pro 2015 13"

This is a bug in 16.10
It did not exist in 16.04
It appears to be for ALL 16.10 kernels to date, ie. from 8/27/2016 onwards

MacBook Pro:
uname --kernel-release --kernel-version
4.8.0-27-generic #29-Ubuntu SMP Thu Oct 20 21:03:13 UTC 2016

MacBook Air:
uname --kernel-release --kernel-version
4.8.0-27-generic #29-Ubuntu SMP Thu Oct 20 21:03:13 UTC 2016

It is triggered by not high temperture but some flawed conclusions
Once kidle_inject launch they eat 50% of available cpu power forever

Perhaps it is triggered by watching flash video from cnn in Chromium

syslog when triggered:
grep powerclamp /var/log/syslog
Nov 17 10:04:22 c89 kernel: [82843.821614] intel_powerclamp: Start idle injection to reduce power

reading temperatures on MacBook Pro:
sensors | egrep "^(Right|Core|TCGC|TB0T)"
Core 0: +69.0°C (high = +105.0°C, crit = +105.0°C)
Core 1: +68.0°C (high = +105.0°C, crit = +105.0°C)
Right Side : 3097 RPM (min = 1299 RPM, max = 6199 RPM)
TB0T: +36.8°C
TCGC: +71.0°C
- the TCGC is GPU which is what supposedly should trigger about 85 °C

Fix to next reboot: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1389077/comments/6
rmmod intel_powerclamp

Across reboot fix: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1389077/comments/12

Just another bug in i915. Don’t expect a fix anytime soon, so just disable if it happens to your computer

Changed in linux (Ubuntu):
status: Incomplete → Confirmed
Richard (ismail-a)
summary: - kidle_inject overly onerous, fans never used on MacBookPro12,1
+ i915 intel_powerclamp consuming 50% cpu kidle_inject
To post a comment you must log in.
This report contains Public information  
Everyone can see this information.

Other bug subscribers

Remote bug watches

Bug watches keep track of this bug in other bug trackers.