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

Tracking: batch query memory control and spill #16615

Closed
5 tasks done
chenzl25 opened this issue May 7, 2024 · 0 comments
Closed
5 tasks done

Tracking: batch query memory control and spill #16615

chenzl25 opened this issue May 7, 2024 · 0 comments
Assignees
Milestone

Comments

@chenzl25
Copy link
Contributor

chenzl25 commented May 7, 2024

Currently, RisingWave batch queries can easily consume too much memory without limitation. This is a great threat to our system's stability. To resolve this issue, we can first implement memory control logic to ensure that if batch queries consume more memory than the reserved memory limit, we can abort a batch query quickly to avoid a potential OOM. The memory check could be implemented on operators that could consume a large amount of memory, e.g. HashAgg, Hash Join, and so on. After we have a memory control logic which means now we know exactly the moment of not enough memory, we can implement a spill-to-disk algorithm for those batch operators.

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

No branches or pull requests

1 participant