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

Add further information to the IdleTuning content #54

Open
SueChaplain opened this issue Jul 3, 2018 · 0 comments
Open

Add further information to the IdleTuning content #54

SueChaplain opened this issue Jul 3, 2018 · 0 comments

Comments

@SueChaplain
Copy link
Contributor

Subject:
https://www.eclipse.org/openj9/docs/xxidletuningminidlewaittime/

Suggestion:
From the slack channel:

"The earliest JVM detects idle state is after it has been idle for around 1 minute (but it is subject to change and it is not exposed to users). So any value less than 1 minute passed to -XX:IdleTuningMinIdleWaitTime gets rounded to 1 minute. Also, because of the way OpenJ9 currently detects its idle state, it may take anywhere around 'n' to 'n+100' secs to detect idle state where 'n' is the value specified to XX:IdleTuningMinIdleWaitTime option."

"When OpenJ9 releases memory pages during idle state, it does not modify internal GC structures which keep track of committed pages. It just de-commits the memory pages to OS using madvise() call. That's the reason Committed value does not reduce while RSS usage goes down during idle state. "

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

No branches or pull requests

1 participant