[WIP] Spark: Make Spark readers function asynchronously for many small files [issue #15287]#15341
Draft
varun-lakhyani wants to merge 3 commits intoapache:mainfrom
Draft
[WIP] Spark: Make Spark readers function asynchronously for many small files [issue #15287]#15341varun-lakhyani wants to merge 3 commits intoapache:mainfrom
varun-lakhyani wants to merge 3 commits intoapache:mainfrom
Conversation
varun-lakhyani
changed the title
varun-lakhyani
changed the title
1 task
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Github issue #15287
Adding AyncTaskOpener which executes an asynchronous opening of tasks and storing them in a queue which base reader can access and take iterators directly from there instead of opening it then.
For lot of smaller files where IO/open overhead is comparable to processing time, parallel opening could make it work faster.
Keeping this specific test in mind to start working on this (Compaction of 10 small files).
iceberg/spark/v4.1/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestRewriteDataFilesProcedure.java
Line 194 in a2802c4
[WIP] High level design and rough implementation done
Pending: Deciding when to go through async path, Exact implementation along with edge cases like making ALL_TASKS_COMPLETE marker surely not reproducible by user, testing it, benchmarking against synchronous flow to verify its betterment, flow or design changes if any.