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

Investigate failed performance test #2892

Open
tillrohrmann opened this issue Mar 12, 2025 · 0 comments
Open

Investigate failed performance test #2892

tillrohrmann opened this issue Mar 12, 2025 · 0 comments
Labels
release-blocker Blocker for the next release

Comments

@tillrohrmann
Copy link
Contributor

The performance test https://github.com/restatedev/e2e-verification-runner/actions/runs/13777670369 failed. What we could gather from the logs is that at some point the test driver was no longer able to send new invocations to the runtime. A few of the idempotent sends timed out consistently for 1,5h. The timeout is set to 1s. The system was still processing other invocations based on the log output.

Based on this, we assume that the system was no longer able to ingest and respond to an idempotent send within 1 second. Somewhere on the way from the ingress to the PP, writing to Bifrost and applying the invocation, we accumulated too much delay. Maybe the system slowed down or there were too many unprocessed messages in Bifrost to respond in time.

We need to look into this problem to better understand what's causing the apparent slow down.

@tillrohrmann tillrohrmann added the release-blocker Blocker for the next release label Mar 12, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
release-blocker Blocker for the next release
Projects
None yet
Development

No branches or pull requests

1 participant