perf: [iceberg] Deduplicate serialized metadata for Iceberg native scan #2933
Conversation
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
mbutrovich
changed the title
mbutrovich
changed the title
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #2933 +/- ##
============================================
+ Coverage 56.12% 59.61% +3.48%
- Complexity 976 1379 +403
============================================
Files 119 167 +48
Lines 11743 15430 +3687
Branches 2251 2550 +299
============================================
+ Hits 6591 9198 +2607
- Misses 4012 4946 +934
- Partials 1140 1286 +146 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Contributor
Author
|
I ran TPC-H SF10 locally and saw: |
hsiang-c
reviewed
Dec 18, 2025
| // Table metadata file path for FileIO initialization | ||
| string metadata_location = 4; | ||
|
|
||
| // Deduplication pools - shared data referenced by index from tasks |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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Outdated suggestions cannot be applied.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.
Which issue does this PR close?
N/A.
Rationale for this change
For the initial implementation of Iceberg native scan we serialized
FileScanTaskobjects on the JVM side 1:1 to the native side for their contents. This results in a lot of duplicate work, particularly with JSON strings like schema. For hundreds, thousands, or even millions of tasks we will 1) convert the schema to JSON, 2) serialize it to protobuf, 3) deserialize it from protobuf, 4) parse it back to JSON.This is all fine for getting correctness working for Iceberg native scans, but we want to start optimizing this for production scale.
What changes are included in this PR?
Many
IcebergScanprotobuf fields are now "pools" of deduplicated values, andIcebergFileScanTaskreferences indices in these pools to extract values from. On the native side, we now cache the extracted values to reduce duplicate JSON parsing.How are these changes tested?
Existing tests.