-
Notifications
You must be signed in to change notification settings - Fork 4.9k
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
Inconsistent CPU Percentage Calculation (Process vs System) #4468
Comments
Thanks @andrewkroh for the great analysis and find. If we make it 100% * number_of_cores that would be more consistent with what we have on Linux, right? I'd vote for that, in that case, so that people can compare the values across systems. |
I changed this to bug so we tackle it for 6.0-GA. |
I'd vote for 100% being the max. I think it would be easier to interpret the data because it doesn't require any knowledge of the number of cores (a value that's not reported AFAIK unless you use correlate it to the Irregardless of the final decision, I think it would be useful to include number of cores as a metric in any CPU related metricsets. |
After the discussion we had yesterday, my vote would be to support both use cases "natively". Perhaps in the
My understanding is that this would be backwards compatible since in the current version With the above, the
Perhaps we could add the normalized values behind an option, like we do for Regardless, I think we should also export |
Any chance this can be backported to 5.x ? |
Hmm, perhaps we can backport the non-BWC bits. Let's first have a concrete PR and we can discuss on it. |
Yeah, this would affect all platforms. |
I just noticed that we use
|
Instead of adding additional
|
@ruflin pointed out that Not of a fan of the abbreviation, but I think we should use |
Change all `system.cpu.*.pct` metrics to be scaled by the number of CPU cores such that the values range on `[0, 100% * number_of_cores]`. This will make the CPU usage percentages from the system cpu metricset consistent with the system process metricset. The documentation for these metrics already stated that on multi-core systems the percentages could be greater than 100%. This makes the code match the docs, but does cause a change in behavior to the user. elastic#4468
I think this can be closed. |
per @andrewkroh
The text was updated successfully, but these errors were encountered: