[SPARK-29454][SQL] Reduce unsafeProjection times when read Parquet file use non-vectorized mode #26106
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
LuciferYang
changed the title
LuciferYang
changed the title
Contributor
Author
|
@cloud-fan @xuanyuanking Could you take a look at the PR, thx~ |
dongjoon-hyun
changed the title
Member
|
ok to test |
| // UnsafeRowParquetRecordReader appends the columns internally to avoid another copy. | ||
| iter.asInstanceOf[Iterator[InternalRow]] | ||
| } else { | ||
| logDebug(s"Falling back to parquet-mr") |
Member
There was a problem hiding this comment.
So, is this PR aiming only for non-vectorized code, @LuciferYang ? If then, please update the PR description.
|
Test build #112069 has finished for PR 26106 at commit
|
LuciferYang
changed the title
LuciferYang
changed the title
Contributor
|
LGTM, merging to master! |
Contributor
Author
|
thx @dongjoon-hyun @cloud-fan ~ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
What changes were proposed in this pull request?
There will be 2 times unsafeProjection convert operation When we read a Parquet data file use non-vectorized mode:
ParquetGroupConvertercall unsafeProjection function to covertSpecificInternalRowtoUnsafeRowevery times when read Parquet data file useParquetRecordReader.ParquetFileFormatwill call unsafeProjection function to covert thisUnsafeRowto anotherUnsafeRowagain when partitionSchema is not empty in DataSourceV1 branch, andPartitionReaderWithPartitionValueswill always do this convert operation in DataSourceV2 branch.In this pr, remove
unsafeProjectionconvert operation inParquetGroupConverterand changeParquetRecordReaderto produceSpecificInternalRowinstead ofUnsafeRow.Why are the changes needed?
The first time convert in
ParquetGroupConverteris redundant andParquetRecordReaderreturn aInternalRow(SpecificInternalRow)is enough.Does this PR introduce any user-facing change?
No.
How was this patch tested?
Unit Test