Skip to content

Conversation

@ligfx
Copy link
Contributor

@ligfx ligfx commented Mar 18, 2024

Fixes issues where the benchmark worker java processes take more memory than the client instance and keep getting hit by the OOM killer / causing SSH connections to get hit by the OOM killer.

Not sure if -Xmx50G should be made dynamic too?

Fixes issues where the benchmark worker java processes take
more memory than the client instance and keep getting hit by
the OOM killer / causing SSH connections to get hit by the OOM
killer.
@ligfx ligfx requested a review from a team as a code owner March 18, 2024 19:17
@ligfx ligfx requested review from StephanDollberg and removed request for a team March 18, 2024 19:17
@voutilad
Copy link
Contributor

Not sure if -Xmx50G should be made dynamic too?

Yes. You're only setting the initial heap. You should be setting -Xmx as well. I think we should follow the practice of setting them to the same value so we don't have unexpected runtime heap growth which can impact the garbage collector. (Once upon a time there were optimizations it could do based on heap size...might still be the case, but it's been a long while since I dove into it.)

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