Skip to content

[Ray Data Optimization]Add environment variable overrides for MAX_SA… #34

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.

Sign up for GitHub

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
ShaochenYu-YW merged 1 commit into from
Jan 15, 2025
Merged

[Ray Data Optimization]Add environment variable overrides for MAX_SA… #34

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion python/ray/data/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@
# We will attempt to slice blocks whose size exceeds this factor *
# target_max_block_size. We will warn the user if slicing fails and we produce
# blocks larger than this threshold.
MAX_SAFE_BLOCK_SIZE_FACTOR = 1.5
MAX_SAFE_BLOCK_SIZE_FACTOR = float(os.environ.get("RAY_DATA_MAX_SAFE_BLOCK_SIZE_FACTOR", "1.5"))
Copy link

@lee1258561 lee1258561 Jan 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it possible to make this as part of the DataContext configuration rather than using the environment variable?

Copy link
Author

@ShaochenYu-YW ShaochenYu-YW Jan 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is not part of data context, so may be harder to do it, and it will serve the same purpose here?

Copy link

@lee1258561 lee1258561 Jan 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mainly for making it consistent with what Ray Data config things


# Dataset will avoid creating blocks smaller than this size in bytes on read.
# This takes precedence over DEFAULT_MIN_PARALLELISM.
Expand Down
Loading