View previous topic :: View next topic |
Author |
Message |
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Tue Jun 19, 2018 5:39 pm Post subject: Intel core i7 7th Gen Overheating |
|
|
Hello,
Recently I bought a TUXEDO Book BX1506 which is equipped with an Intel Kaby Lake CPU: Intel Core i7-7700T (4x 2.90-3.80 GHz Quad-Core, 8-Threads, 8 MB Cache, 35W TDP) processor.
After installing Gentoo and KUbuntu 18.04 LTS, I notice that I get a lot of overheating notifications in my Gentoo dmesg log. This happens mainly during the compilation of large programs (MAKEOPTS="-j5").
When I'm surfing under KDE with Firefox and looking at youtube films, then the fan always turns on (but do not get any dmesg notifications yet).
Dmesg snippet:
Code: | [ 901.311962] CPU6: Core temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311963] CPU2: Core temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311964] CPU3: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311965] CPU1: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311966] CPU7: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311967] CPU0: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311967] CPU5: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311968] CPU4: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311969] CPU2: Package temperature above threshold, cpu clock throttled
(total events = 1)
[ 901.311971] mce: [Hardware Error]: Machine check events logged
[ 901.315933] CPU2: Core temperature/speed normal
[ 901.315934] CPU1: Package temperature/speed normal
[ 901.315935] CPU3: Package temperature/speed normal
[ 901.315936] CPU0: Package temperature/speed normal
[ 901.315936] CPU5: Package temperature/speed normal
[ 901.315937] CPU7: Package temperature/speed normal
[ 901.315938] CPU4: Package temperature/speed normal
[ 901.315938] CPU2: Package temperature/speed normal
[ 901.315940] mce: [Hardware Error]: Machine check events logged
[ 901.343044] CPU6: Core temperature/speed normal
[ 1196.527385] kworker/dying (5165) used greatest stack depth: 12440 bytes
left
[ 1201.316957] CPU3: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316959] CPU0: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316960] CPU5: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316962] CPU2: Core temperature above threshold, cpu clock throttled
(total events = 27443)
[ 1201.316963] CPU4: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316964] CPU1: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316965] CPU7: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316966] CPU2: Package temperature above threshold, cpu clock throttled
(total events = 35574)
[ 1201.316968] mce_notify_irq: 1 callbacks suppressed
[ 1201.316969] mce: [Hardware Error]: Machine check events logged
[ 1201.347961] CPU6: Core temperature/speed normal
[ 1201.347964] CPU6: Package temperature/speed normal
[ 1201.347966] mce: [Hardware Error]: Machine check events logged
[ 1501.322945] CPU2: Core temperature/speed normal
[ 1501.322946] CPU3: Package temperature/speed normal
[ 1501.322947] CPU1: Package temperature/speed normal
[ 1501.322948] CPU4: Package temperature/speed normal
[ 1501.322948] CPU5: Package temperature/speed normal
[ 1501.322949] CPU7: Package temperature/speed normal
[ 1501.322950] CPU0: Package temperature/speed normal
[ 1501.322953] CPU2: Package temperature/speed normal
[ 1501.322955] mce: [Hardware Error]: Machine check events logged
[ 1501.347933] CPU6: Core temperature above threshold, cpu clock throttled
(total events = 56135)
[ 1501.347979] CPU6: Package temperature above threshold, cpu clock throttled
(total events = 69968)
[ 1501.351817] mce: [Hardware Error]: Machine check events logged
[ 1501.373973] CPU6: Core temperature/speed normal
[ 1501.373977] CPU6: Package temperature/speed normal
[ 1801.324929] CPU0: Package temperature/speed normal
[ 1801.324930] CPU4: Package temperature/speed normal
[ 1801.324931] CPU7: Package temperature/speed normal
[ 1801.324932] CPU3: Package temperature/speed normal
[ 1801.324933] CPU2: Core temperature/speed normal
[ 1801.324936] CPU2: Package temperature/speed normal
[ 1801.324940] mce_notify_irq: 1 callbacks suppressed
[ 1801.324940] mce: [Hardware Error]: Machine check events logged
[ 1801.324958] CPU1: Package temperature/speed normal
[ 1801.324959] CPU5: Package temperature/speed normal
[ 1801.390935] CPU6: Core temperature/speed normal
[ 1801.390938] CPU6: Package temperature/speed normal
[ 1801.390941] mce: [Hardware Error]: Machine check events logged
[ 1808.075933] CPU7: Core temperature above threshold, cpu clock throttled
(total events = 25567)
[ 1808.075934] CPU3: Core temperature above threshold, cpu clock throttled
(total events = 25567)
[ 1808.076951] CPU3: Core temperature/speed normal
[ 1808.076952] CPU7: Core temperature/speed normal
|
I have installed the Intel Microcode package, but this solves nothing yet.
When I'm using KUbuntu, then the fan is switched on much less.
Is there someone who can help me out?
Regards,
GenHeDi _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
bunder Bodhisattva
Joined: 10 Apr 2004 Posts: 5934
|
Posted: Tue Jun 19, 2018 6:06 pm Post subject: |
|
|
Try turning off turbo boost.
Code: | echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo |
_________________
Neddyseagoon wrote: | The problem with leaving is that you can only do it once and it reduces your influence. |
banned from #gentoo since sept 2017 |
|
Back to top |
|
|
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Wed Jun 20, 2018 4:27 pm Post subject: |
|
|
Hello bunder,
I had a look in the directory butthis file does not exist in my installation
Code: | # ls -l /sys/devices/system/cpu/
totaal 0
drwxr-xr-x 9 root root 0 20 jun 2018 cpu0
drwxr-xr-x 9 root root 0 20 jun 2018 cpu1
drwxr-xr-x 9 root root 0 20 jun 2018 cpu2
drwxr-xr-x 9 root root 0 20 jun 2018 cpu3
drwxr-xr-x 9 root root 0 20 jun 2018 cpu4
drwxr-xr-x 9 root root 0 20 jun 2018 cpu5
drwxr-xr-x 9 root root 0 20 jun 2018 cpu6
drwxr-xr-x 9 root root 0 20 jun 2018 cpu7
drwxr-xr-x 10 root root 0 20 jun 18:17 cpufreq
drwxr-xr-x 2 root root 0 20 jun 18:17 cpuidle
drwxr-xr-x 2 root root 0 20 jun 18:17 hotplug
-r--r--r-- 1 root root 4096 20 jun 18:17 isolated
-r--r--r-- 1 root root 4096 20 jun 18:17 kernel_max
drwxr-xr-x 2 root root 0 20 jun 18:17 microcode
-r--r--r-- 1 root root 4096 20 jun 18:17 modalias
-r--r--r-- 1 root root 4096 20 jun 18:17 offline
-r--r--r-- 1 root root 4096 20 jun 18:17 online
-r--r--r-- 1 root root 4096 20 jun 18:17 possible
drwxr-xr-x 2 root root 0 20 jun 18:17 power
-r--r--r-- 1 root root 4096 20 jun 18:17 present
-rw-r--r-- 1 root root 4096 20 jun 2018 uevent
drwxr-xr-x 2 root root 0 20 jun 18:17 vulnerabilities
|
In my KUbuntu installation it does exist and it has the value of 0
How do I get my Gentoo directory structure up to spec's?
Regards _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
bunder Bodhisattva
Joined: 10 Apr 2004 Posts: 5934
|
Posted: Wed Jun 20, 2018 4:46 pm Post subject: |
|
|
I think you might be missing CONFIG_X86_INTEL_PSTATE=y
Cheers _________________
Neddyseagoon wrote: | The problem with leaving is that you can only do it once and it reduces your influence. |
banned from #gentoo since sept 2017 |
|
Back to top |
|
|
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Sat Jun 23, 2018 8:07 am Post subject: |
|
|
You were right, it was not set. I turned it into y and now I can turn off turbo boost.
Although after a reboot it is turned on again, how to deal with that?
Yesterday I forced a huge compiling job on this laptop but unfortunately I have still overheating messages in my dmeg.
Although way less than before.
I think that still other kernel parameters are not properly set yet, like "Processor Clocking Controle interface driver" is not set yet.
Is there a proper way to double check the necessary settings / value's? I followed the instructions of the Gentoo AMD64 Handbook.
Regards _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
bunder Bodhisattva
Joined: 10 Apr 2004 Posts: 5934
|
Posted: Sat Jun 23, 2018 9:28 am Post subject: |
|
|
I wrote a script for this... https://github.com/bunder2015/scripts/blob/master/linux/no-turbo.sh
if you put it into /etc/local.d then it should run on startup, but you can also add it to cron so it runs periodically (as sometimes it can turn itself back on, my laptop does when I unplug/replug). _________________
Neddyseagoon wrote: | The problem with leaving is that you can only do it once and it reduces your influence. |
banned from #gentoo since sept 2017 |
|
Back to top |
|
|
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Sun Jun 24, 2018 11:10 am Post subject: |
|
|
Thanks a lot,
I did put your script in my /etc/local.d and it works like a charm (after I put a .start suffix in the filename )
But after this modification I see still overheating messages in my dmesg.
Any idea how to proceed? _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
Jaglover Watchman
Joined: 29 May 2005 Posts: 8291 Location: Saint Amant, Acadiana
|
|
Back to top |
|
|
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Sun Jun 24, 2018 11:26 am Post subject: |
|
|
What is your advice regarding the "force powersave governor" part?
Regards, _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
bunder Bodhisattva
Joined: 10 Apr 2004 Posts: 5934
|
Posted: Sun Jun 24, 2018 12:22 pm Post subject: |
|
|
I haven't had to do anything other than turn turbo off. Are you sure your cooling is working okay?
This thing looks like it was made by Clevo. If you press Fn + 1 does the fan spin up to full speed? _________________
Neddyseagoon wrote: | The problem with leaving is that you can only do it once and it reduces your influence. |
banned from #gentoo since sept 2017 |
|
Back to top |
|
|
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Sun Jun 24, 2018 1:06 pm Post subject: |
|
|
Fn + 1 does the fan spin up to full speed > confirm
I have also KUbuntu 18.04 LTS running on same system. When I'm running KUbuntu there are no logs in dmesg of thermal heating at all.
Regards, _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
Hu Moderator
Joined: 06 Mar 2007 Posts: 21624
|
Posted: Sun Jun 24, 2018 3:04 pm Post subject: |
|
|
When you run Kubuntu 18.04, are you using the system in a way that keeps the CPUs running at maximum load for minutes or hours at a time? The binary distributions generally don't put nearly as much load on your system as a big Gentoo emerge job. |
|
Back to top |
|
|
GenHeDi Tux's lil' helper
Joined: 02 Jan 2016 Posts: 132
|
Posted: Sun Jun 24, 2018 4:43 pm Post subject: |
|
|
Your right, I don't do heavy stuff on KUbuntu like the emerge jobs on Gentoo. _________________ Nulla tenaci invia est via |
|
Back to top |
|
|
fxkrait n00b
Joined: 30 Jul 2018 Posts: 15 Location: DRPK
|
Posted: Thu Aug 02, 2018 4:38 am Post subject: |
|
|
I have a Clevo laptop as well, and have no issues with my CPU overheating.
Laptops are just fine for compiling all day.
I can turbo (not at max) and stay under 90 C.
Look into re-applying your thermal paste with "liquid metal", it will drastically improve your cooling capabilities. _________________ A great painter does not content himself by affecting us with his masterpieces; ultimately, he succeeds in changing the landscape of our minds. Once a miniaturist's artistry enters our souls this way, it becomes the criterion for the beauty of our world. |
|
Back to top |
|
|
devsk Advocate
Joined: 24 Oct 2003 Posts: 2995 Location: Bay Area, CA
|
Posted: Fri Aug 03, 2018 6:03 am Post subject: |
|
|
Try undervolting your CPU. See: https://github.com/georgewhewell/undervolt
I am doing a -140mV undervolt on my Dell XPS and its plenty stable. It may sound counter-intuitive but undervolting the CPU actually gave me 15% more performance from the CPU because temperature thresholds where throttling happened, were achieved with a higher CPU frequency.
BTW, throttling is a protection mechanism. CPU microcode just degrades the performance by few hundred Mhz's to let the CPU cool down. So, as such its not a longevity hit on the CPU as much as its a peak performance hit. |
|
Back to top |
|
|
n05ph3r42 Tux's lil' helper
Joined: 11 Jul 2016 Posts: 134
|
|
Back to top |
|
|
|