Skip to content
This repository has been archived by the owner on Jul 24, 2024. It is now read-only.

Run scatter region in parallel #271

Closed
kennytm opened this issue May 9, 2020 · 1 comment
Closed

Run scatter region in parallel #271

kennytm opened this issue May 9, 2020 · 1 comment
Labels
type/feature-request New feature or request

Comments

@kennytm
Copy link
Collaborator

kennytm commented May 9, 2020

Feature Request

Describe your feature request related problem:

Currently "scatter" is run immediately after "split", all in a single thread. While "split" must be serial, "scatter" does not need to be.

Describe the feature you'd like:

Change (*RegionSplitter).Split() to:

  1. Perform all split without any scatter
  2. In parallel (with some concurrency limitation), perform scatter.

Describe alternatives you've considered:

Teachability, Documentation, Adoption, Migration Strategy:

@kennytm kennytm added the type/feature-request New feature or request label May 9, 2020
@kennytm
Copy link
Collaborator Author

kennytm commented May 9, 2020

We already scatter in parallel to some degree after #167.

  • The ScatterRegion only inserts a "scatter" operator, which is executed asynchronously. (This is also why we need to "wait" for the scatter operation to be completed in the end.)
  • We perform the "wait" every 128 regions (the "128" is controlled by --concurrency, the count is before splitting).

@kennytm kennytm closed this as completed May 9, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
type/feature-request New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant