Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Wrong Core Numbers in the Output [Asus WS-C621E-SAGE] #301

Open
cyprix opened this issue Dec 22, 2020 · 8 comments
Open

Wrong Core Numbers in the Output [Asus WS-C621E-SAGE] #301

cyprix opened this issue Dec 22, 2020 · 8 comments

Comments

@cyprix
Copy link

cyprix commented Dec 22, 2020

HW:
Motherboard: Asus WS-C621E-SAGE
CPUs: 2 x Xeon Platinum 24-core ES Samples QL1K
Number of CPU Threads: 96
grep ^processor /proc/cpuinfo | wc -l 96

OS
Kernel: 5.4.0-58-generic
System: Ubuntu 20.04.1 64-bit
lm-sensors packages versions:

libsensors5:amd64    1:3.6.0-2ubuntu1           amd64        library to read temperature/voltage/fan sensors
libsensors5:i386     1:3.6.0-2ubuntu1           i386         library to read temperature/voltage/fan sensors
lm-sensors           1:3.6.0-2ubuntu1           amd64        utilities to read temperature/voltage/fan sensors

Sensors command output shows only 30+30 ( total: 60 )cores, but should be 96 as I think:

sensors
coretemp-isa-0001
Adapter: ISA adapter
Package id 1:  +48.0°C  (high = +81.0°C, crit = +91.0°C)<br>
Core 0:        +47.0°C  (high = +81.0°C, crit = +91.0°C)
Core 1:        +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 2:        +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 3:        +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 4:        +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 5:        +48.0°C  (high = +81.0°C, crit = +91.0°C)
Core 8:        +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 9:        +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 10:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 11:       +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 12:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 13:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 16:       +47.0°C  (high = +81.0°C, crit = +91.0°C)
Core 17:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 18:       +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 19:       +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 20:       +47.0°C  (high = +81.0°C, crit = +91.0°C)
Core 21:       +47.0°C  (high = +81.0°C, crit = +91.0°C)
Core 24:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 25:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
Core 26:       +47.0°C  (high = +81.0°C, crit = +91.0°C)
Core 27:       +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 28:       +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 29:       +46.0°C  (high = +81.0°C, crit = +91.0°C)
coretemp-isa-0000
Adapter: ISA adapter
Package id 0:  +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 0:        +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 1:        +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 2:        +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 3:        +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 4:        +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 5:        +45.0°C  (high = +81.0°C, crit = +91.0°C)
Core 8:        +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 9:        +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 10:       +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 11:       +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 12:       +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 13:       +44.0°C  (high = +81.0°C, crit = +91.0°C)
Core 16:       +44.0°C  (high = +81.0°C, crit = +91.0°C)
Core 17:       +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 18:       +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 19:       +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 20:       +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 21:       +44.0°C  (high = +81.0°C, crit = +91.0°C)
Core 24:       +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 25:       +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 26:       +42.0°C  (high = +81.0°C, crit = +91.0°C)
Core 27:       +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 28:       +43.0°C  (high = +81.0°C, crit = +91.0°C)
Core 29:       +43.0°C  (high = +81.0°C, crit = +91.0°C)```
@cyprix cyprix changed the title Wrong Core Number in the Output Wrong Core Numbers in the Output [Asus WS-C621E-SAGE] Dec 22, 2020
@abucodonosor
Copy link

@cyprix

coretemp module is maintained in the kernel tree. You may want to poke the developers there.

@abucodonosor
Copy link

:~/kernel/linux$ scripts/get_maintainer.pl ./drivers/hwmon/coretemp.c
Fenghua Yu fenghua.yu@intel.com (maintainer:CORETEMP HARDWARE MONITORING DRIVER)
Jean Delvare jdelvare@suse.com (maintainer:HARDWARE MONITORING)
Guenter Roeck linux@roeck-us.net (maintainer:HARDWARE MONITORING)
linux-hwmon@vger.kernel.org (open list:CORETEMP HARDWARE MONITORING DRIVER)
linux-kernel@vger.kernel.org (open list)

@romanstingler
Copy link

same here with 2x Xeon Platinum 8260

@cyprix
Copy link
Author

cyprix commented Jan 26, 2021

Hi @romanstingler can you provide the /proc/cpuinfo output?
I find that the lm-sensors display only the HW cores (That's right)
And I think the core number obtained from the procfs ( cpuinfo ).
As you can see the cores groups by 6 ( Core 0-6,8-13,16-21,24-29). Similar to the Xeon E5-2650L v3.
In my thoughts, it is not the lm-sensors bug or issue, due that it provides the information from procfs.

@romanstingler
Copy link

I know that sensors just displays physical cores.

cpuinfo shows me
cpu cores : 24
which is true per cpu

the cores do not group by 6 (where do you take the information)!

do you mean in lscpu

NUMA node0 CPU(s):               0-23,48-71
NUMA node1 CPU(s):               24-47,72-95

Linux takes the physical cores first and then the logical!

The 2650Lv3 has 12 physical cores and
maybe your numa nodes have separated the cores according to your finding but normally the Numa nodes are per CPU (except very large core count).

cpuinfo.txt

@cyprix
Copy link
Author

cyprix commented Feb 1, 2021

Hi @romanstingler
Sorry, I wrote incorrect.
Please run this command
grep "core id" cpuinfo.txt | sort -V | uniq
And you will see that core id groups with 6 (0,1,2,3,4,5) and next group starts from 8

@romanstingler
Copy link

blackout@Workstation ~/Videos % grep "core id" cpuinfo.txt | sort -V | uniq
core id : 0
core id : 1
core id : 2
core id : 3
core id : 4
core id : 5
core id : 8
core id : 9
core id : 10
core id : 11
core id : 12
core id : 13
core id : 16
core id : 17
core id : 18
core id : 19
core id : 20
core id : 21
core id : 24
core id : 25
core id : 26
core id : 27
core id : 28
core id : 29

@romanstingler
Copy link

and why was is correctly displayed months ago ??

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants