Skip to content

Conversation

@rickyyx
Copy link
Member

@rickyyx rickyyx commented Nov 13, 2023

Why are these changes needed?

We were tracking stored tasks event size from ByteSizeLong() calls, which is showing high overheads. Since we are already tracking the number of task attempts, we could get a proxy over the size and thus dropping the size tracking completely.

Related issue number

Closes #41027

Checks

  • I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
  • I've run scripts/format.sh to lint the changes in this PR.
  • I've included any doc changes needed for https://docs.ray.io/en/master/.
    • I've added any new APIs to the API Reference. For example, if I added a
      method in Tune, I've added it in doc/source/tune/api/ under the
      corresponding .rst file.
  • I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
  • Testing Strategy
    • Unit tests
    • Release tests
    • This PR is not tested :(

Signed-off-by: rickyyx <[email protected]>
@rickyyx rickyyx requested a review from a team as a code owner November 13, 2023 23:40
Signed-off-by: rickyyx <[email protected]>
@rickyyx
Copy link
Member Author

rickyyx commented Nov 13, 2023

Comparing the processing time for the task events thread with release tests: https://buildkite.com/ray-project/release/builds/1074

@rkooo567 rkooo567 merged commit 7a75d09 into ray-project:master Nov 17, 2023
ujjawal-khare pushed a commit to ujjawal-khare-27/ray that referenced this pull request Nov 29, 2023
…#41108)

We were tracking stored tasks event size from ByteSizeLong() calls, which is showing high overheads. Since we are already tracking the number of task attempts, we could get a proxy over the size and thus dropping the size tracking completely.
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.

[Core] ByteSizeLong is too expensive, leading to high CPU usage in the GCS task events thread.

2 participants