CPU Stress Tests + Temp Readings Possible

Hello Everyone,

I have an older Dell XPS 13 9350 model laptop (that’s 6 years old at this point) that I plan on opening up, doing a good cleaning, and replacing the thermal paste. However, before I do any cleaning I wanted to grab some current data / metrics on how my CPU temps are during heavy loads today.

**Question:**
I know Windows has a few utilities for this purpose, however are there any good CPU Stress Tests + Temp  monitoring utilities for doing this in Linux? As I said, I would like to get a nice snapshot before / after I do the cleaning + new thermal paste installation. 

If anyone that could offer any feedback or assistance, it would be greatly appreciated!

Thanks,
Asif

Use the stress package to stress test CPU. To perform a stress test with stress, simply enter the following command where the number used in --cpu is the amount of threads to start. To fully stress the CPU, this should be the total number of CPU cores or double that if the CPU supports hyper-threading. You can obtain the appropriate number to use by entering getconf _NPROCESSORS_ONLN:

sudo pacman -S stress
stress --cpu 8 #press Ctrl + C to stop

Use the lm_sensors package to scan various hardware sensors to report there temperature status:

sudo pacman -S lm_sensors
sudo sensors-detect #to configure lm_sensors
watch sensors #to watch CPU Temp in real-time

You can also use mprime to stress the cpu (and ram if you want).

I use s-tui for basic testing/monitoring. A nice terminal tool with some nice settings

sudo pacman -S s-tui

PS: it currently has an issue where the CPU frequency doesn’t show in graph, because of a Python package update, that will soon be resolved, in the meantime check this if you want to have CPU frequency graph

2 Likes

That’s nice! I usually use ksysguard or turbostat to watch the frequency.

s-tui is really nice - Thanks for the tip!

Indeed :wink:

I like how you can configure the graphs, the stress test (made with stress).