Skip to content

Workers submit a reply to the scheduler if replica removal was rejected #5356

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

Merged
merged 8 commits into from
Sep 28, 2021

Conversation

fjetter
Copy link
Member

@fjetter fjetter commented Sep 27, 2021

Closes #5265

@crusaderky
Copy link
Collaborator

crusaderky commented Sep 28, 2021

Could you do the following changes to test_worker.py:

  1. change _remove_replicas to immediately delete the server side key
  2. change test_remove_replica_while_computing to test that the server side key disappears immediately and then reappears after a while
  3. change test_remove_replica_simple to test that the key does not reappear after a while

Co-authored-by: crusaderky <crusaderky@gmail.com>
fjetter and others added 3 commits September 28, 2021 16:51
Co-authored-by: crusaderky <crusaderky@gmail.com>
…tter/distributed into gh5265/race_condition_remove_replica
@crusaderky crusaderky merged commit 2701d4a into dask:main Sep 28, 2021
@fjetter fjetter deleted the gh5265/race_condition_remove_replica branch September 30, 2021 11:58
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.

Race condition in remove-replicas could make you lose the last replica of a key
2 participants