Skip to content

GH-3226: Improve performance of InternalParquetRecordReader (1%) #3227

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

GH-3226: Improve performance of InternalParquetRecordReader (1%) #3227

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 24 additions & 4 deletions parquet-hadoop/src/main/java/org/apache/parquet/hadoop/InternalParquetRecordReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,6 @@
import java.util.Optional;
import java.util.PrimitiveIterator;
import java.util.Set;
import java.util.stream.LongStream;
import org.apache.hadoop.conf.Configuration;
import org.apache.parquet.ParquetReadOptions;
import org.apache.parquet.column.page.PageReadStore;
Expand Down Expand Up @@ -320,21 +319,42 @@ private void resetRowIndexIterator(PageReadStore pages) {
if (pages.getRowIndexes().isPresent()) {
rowIdxInRowGroupItr = pages.getRowIndexes().get();
} else {
rowIdxInRowGroupItr = LongStream.range(0, pages.getRowCount()).iterator();
rowIdxInRowGroupItr = new LongIterator(pages.getRowCount());
}
// Adjust the row group offset in the `rowIndexWithinRowGroupIterator` iterator.
final long rowGroupRowIdxOffsetValue = rowGroupRowIdxOffset.get();
this.rowIdxInFileItr = new PrimitiveIterator.OfLong() {
public long nextLong() {
return rowGroupRowIdxOffset.get() + rowIdxInRowGroupItr.nextLong();
return rowGroupRowIdxOffsetValue + rowIdxInRowGroupItr.nextLong();
}

public boolean hasNext() {
return rowIdxInRowGroupItr.hasNext();
}

public Long next() {
return rowGroupRowIdxOffset.get() + rowIdxInRowGroupItr.next();
return rowGroupRowIdxOffsetValue + rowIdxInRowGroupItr.next();
}
};
}

private static class LongIterator implements PrimitiveIterator.OfLong {

private final long maxValue;
private long currentValue = 0;

public LongIterator(long maxValue) {
this.maxValue = maxValue;
}

@Override
public long nextLong() {
return currentValue++;
}

@Override
public boolean hasNext() {
return currentValue < maxValue;
}
}
}