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

High CPU usage to the extent where the node becomes unresponsive #2062

Closed
masih opened this issue Jun 30, 2023 · 3 comments
Closed

High CPU usage to the extent where the node becomes unresponsive #2062

masih opened this issue Jun 30, 2023 · 3 comments
Assignees

Comments

@masih
Copy link
Member

masih commented Jun 30, 2023

Observed on Inga on 30th of June between 0930-1130 UTC on inga.

Check grafana metrics, logs and investigate root cause. For now, we should not roll out 0.7.5 to prod.

@masih masih changed the title Release 0.7.5 seem to cause high CPU usage to the extent where the node becomes unresponsive High CPU usage to the extent where the node becomes unresponsive Jun 30, 2023
@masih
Copy link
Member Author

masih commented Jun 30, 2023

Updated the issue title as this occurs on 0.7.3 too.

PProf/profile on the node seems to suggest locking contention with leveldb lookups
Screenshot 2023-06-30 at 14 14 34

Which points to index counter? Investigating.

@masih
Copy link
Member Author

masih commented Jun 30, 2023

Update: Excluding index counter from find server seems to have resolved the CPU contention. Working on a fix in #2067

Impact before and after deployment:

image

@gammazero
Copy link
Collaborator

Fixed by #2101 and by integration of new provider cache into dhstore and indexstar.

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

2 participants