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

Fixed bug in performance boost logic. #131

Merged
merged 1 commit into from
Nov 28, 2020

Conversation

dfuehrer
Copy link
Contributor

Now boosts when max core usage is above 75% rather than max core usage close to 75%.

Now boosts when max core usage is above 75% rather than max core usage
close to 75%
@AdnanHodzic
Copy link
Owner

Good point, but why didn't you make same changes for set_powersave function?

Interestingly enough I've just found that if on powersave mode, and if I stress my CPU (stress --cpu 8 --io 4 --vm 4 --timeout 45) max frequency I get per core is only only in range: 2100-2250MHz out of max 4600MHz, i,e:

CPU max frequency: 4600 MHz
CPU min frequency: 400 MHz

	 Usage  Temperature  Frequency
CPU0:	100.0%     68 °C     2123 MHz
CPU1:	100.0%     68 °C     2124 MHz
CPU2:	100.0%     66 °C     2125 MHz
CPU3:	100.0%     70 °C     2127 MHz
CPU4:	100.0%     68 °C     2129 MHz
CPU5:	100.0%     68 °C     2128 MHz
CPU6:	 99.0%     66 °C     2127 MHz
CPU7:	100.0%     70 °C     2120 MHz

Any idea about this?

@dfuehrer
Copy link
Contributor Author

I didn't change the powersave logic since it has it boost when the max core usage is close to 100%. If I changed it it would make it more like boosting when the max core usage is over 95%.

I didn't notice that but it does happen on my laptop too when it is set to the shedutil governor. My best guess is that the max cpu frequency for the power saving governors is less than the max frequency overall but i don't know why it wouldn't update based on the governor used. I'm not very familiar with this stuff.

@AdnanHodzic
Copy link
Owner

I didn't change the powersave logic since it has it boost when the max core usage is close to 100%. If I changed it it would make it more like boosting when the max core usage is over 95%.

Make sense.

I didn't notice that but it does happen on my laptop too when it is set to the shedutil governor. My best guess is that the max cpu frequency for the power saving governors is less than the max frequency overall but i don't know why it wouldn't update based on the governor used. I'm not very familiar with this stuff.

Agreed, I also think this is the reason. I'll investigate this further when I have time.

Thank you for your contribution!

@AdnanHodzic AdnanHodzic merged commit d0aeb8c into AdnanHodzic:master Nov 28, 2020
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

Successfully merging this pull request may close these issues.

2 participants