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

Calculate latency in stress as soon as success is returned #4527

Merged
merged 1 commit into from
Sep 8, 2022

Conversation

sadhansood
Copy link
Contributor

Today, we have a couple issues with latency recording:

  1. During retries we are not calculating latency from when the request was submitted but instead when the success was returned. This is likely causing the shared counter workload to show up with really good pXX latency numbers since it is the one which is getting retried the most (due to timeouts)
  2. We wait a little longer to record latency (which is based on an event loop). This diff fixes the bahvior and calculates it as soon as success is returned
  3. We are tagging latencies with next workload type instead of the current one. This diff fixes the behavior as well

@sadhansood sadhansood marked this pull request as ready for review September 8, 2022 17:42
@sadhansood sadhansood enabled auto-merge (squash) September 8, 2022 17:46
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.

3 participants