Read the footers in parallel when reading multiple Parquet files #17957
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
github-actions
bot
added
libcudf
vuule
added
Performance
ttnghia
approved these changes
Feb 11, 2025
pmattione-nvidia
approved these changes
Feb 11, 2025
…opt-parallel-metadata-ctors
…opt-parallel-metadata-ctors
3 tasks
vuule
force-pushed
the
opt-parallel-metadata-ctors
branch
from
058482b to
e321f66
Compare
|
/merge |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Depends on #18018
When reading multiple files, all data(i.e. pages) IO is performed in the same "batch", allowing parallel IO operations (provided by kvikIO). However, footers are read serially, leading to poor performance when reading many files. This is especially pronounced for IO that benefits from high level of parallelism.
This PR performs footer reading/parsing asynchronously using an internal thread pool. The pool size can be controlled with an environment variable
LIBCUDF_NUM_HOST_WORKERS.Checklist