[GLUTEN-11782][CORE] Optimize parquet metadata validation by sampling#12042
Open
Yao-MR wants to merge 2 commits intoapache:mainfrom
Open
[GLUTEN-11782][CORE] Optimize parquet metadata validation by sampling#12042Yao-MR wants to merge 2 commits intoapache:mainfrom
Yao-MR wants to merge 2 commits intoapache:mainfrom
Conversation
|
Run Gluten Clickhouse CI on x86 |
Yao-MR
force-pushed
the
feature/optimize-parquet-metadata-validation-sampling
branch
from
706c87f to
970fb06
Compare
|
Run Gluten Clickhouse CI on x86 |
1 similar comment
|
Run Gluten Clickhouse CI on x86 |
Yao-MR
changed the title
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
… root paths When a table has many partitions, the metadata validation checks every root path with `fileLimit` files each, resulting in excessive I/O cost. This patch introduces a sampling mechanism that selects a percentage of root paths for validation instead of checking all of them. The file limit is distributed evenly across the sampled paths. Key changes: - Add config `spark.gluten.sql.fallbackUnexpectedMetadataParquet.samplePercentage` with default value 0.1 (10% sampling) - Use evenly spaced interval sampling for good partition coverage - Add unit tests for the sampling logic
Yao-MR
force-pushed
the
feature/optimize-parquet-metadata-validation-sampling
branch
from
51b280f to
e99a01e
Compare
|
Run Gluten Clickhouse CI on x86 |
Contributor
Author
|
hi @jinchengchenghh, make a optimized sample validation which can improve the performance. |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
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.
What changes are proposed in this pull request?
When a table has many partitions, the metadata validation checks every root path with
fileLimitfiles each, resulting in excessive I/O cost.This patch introduces a sampling mechanism that selects a percentage of root paths for validation instead of checking all of them. The file limit is distributed evenly across the sampled paths.
Key changes:
spark.gluten.sql.fallbackUnexpectedMetadataParquet.samplePercentagewith default value 0.1 (10% sampling)How was this patch tested?
Existing tests in ParquetEncryptionDetectionSuite continue to pass without modification.
Was this patch authored or co-authored using generative AI tooling?
ISSUE: #11782