Skip to content
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

Jump to bottom

Optimizations in parquet file page materialization #5582

Merged
merged 8 commits into from
Jun 17, 2024
Merged

Optimizations in parquet file page materialization #5582

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
c8e1d53
Optimized ToPage for multiple types
malhotrashivam Jun 6, 2024
f1bdc16
Moved materializers to separate package and added replicators
malhotrashivam Jun 6, 2024
732e907
Merge branch 'main' into sm-string-opt
malhotrashivam Jun 6, 2024
e53a4b5
Resolving review comments
malhotrashivam Jun 17, 2024
bf9283a
Minor refactoring
malhotrashivam Jun 17, 2024
67b61a7
Added more replicators
malhotrashivam Jun 17, 2024
2b2de0c
Resolving more review comments
malhotrashivam Jun 17, 2024
54629d6
Merge branch 'main' into sm-string-opt
malhotrashivam Jun 17, 2024
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
2 changes: 2 additions & 0 deletions extensions/parquet/base/build.gradle
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,8 @@ dependencies {
implementation project(':extensions-parquet-compression')
implementation project(':Base')
implementation project(':Util')
implementation project(':engine-time')
implementation project(':Configuration')
implementation depCommonsIo

compileOnly depAnnotations
Expand Down
8 changes: 4 additions & 4 deletions extensions/parquet/base/src/main/java/io/deephaven/parquet/base/ColumnChunkReaderImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ final class ColumnChunkReaderImpl implements ColumnChunkReader {
private final OffsetIndexReader offsetIndexReader;
private final List<Type> fieldTypes;
private final Function<SeekableChannelContext, Dictionary> dictionarySupplier;
private final PageMaterializerFactory nullMaterializerFactory;
private final PageMaterializerFactory pageMaterializerFactory;
private final URI columnChunkURI;
/**
* Number of rows in the row group of this column chunk.
Expand Down Expand Up @@ -81,7 +81,7 @@ final class ColumnChunkReaderImpl implements ColumnChunkReader {
}
this.fieldTypes = fieldTypes;
this.dictionarySupplier = new SoftCachingFunction<>(this::getDictionary);
this.nullMaterializerFactory = PageMaterializer.factoryForType(path.getPrimitiveType().getPrimitiveTypeName());
this.pageMaterializerFactory = PageMaterializer.factoryForType(path.getPrimitiveType());
this.numRows = numRows;
this.version = version;
if (columnChunk.isSetFile_path() && FILE_URI_SCHEME.equals(rootURI.getScheme())) {
Expand Down Expand Up @@ -289,7 +289,7 @@ public ColumnPageReader next(@NotNull final SeekableChannelContext channelContex
final Function<SeekableChannelContext, Dictionary> pageDictionarySupplier =
getPageDictionarySupplier(pageHeader);
return new ColumnPageReaderImpl(columnName, channelsProvider, decompressor, pageDictionarySupplier,
nullMaterializerFactory, path, getURI(), fieldTypes, dataOffset, pageHeader, numValuesInPage);
pageMaterializerFactory, path, getURI(), fieldTypes, dataOffset, pageHeader, numValuesInPage);
} catch (IOException e) {
throw new UncheckedDeephavenException("Error reading page header at offset " + headerOffset + " for " +
"column: " + columnName + ", uri: " + getURI(), e);
Expand Down Expand Up @@ -364,7 +364,7 @@ public ColumnPageReader getPageReader(final int pageNum, final SeekableChannelCo
final Function<SeekableChannelContext, Dictionary> pageDictionarySupplier =
getPageDictionarySupplier(pageHeader);
return new ColumnPageReaderImpl(columnName, channelsProvider, decompressor, pageDictionarySupplier,
nullMaterializerFactory, path, getURI(), fieldTypes, dataOffset, pageHeader,
pageMaterializerFactory, path, getURI(), fieldTypes, dataOffset, pageHeader,
getNumValues(pageHeader));
} catch (final IOException e) {
throw new UncheckedDeephavenException("Error reading page header for page number " + pageNum +
Expand Down
4 changes: 2 additions & 2 deletions extensions/parquet/base/src/main/java/io/deephaven/parquet/base/ColumnPageReaderImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
import io.deephaven.UncheckedDeephavenException;
import io.deephaven.base.Pair;
import io.deephaven.base.verify.Require;
import io.deephaven.parquet.base.materializers.IntMaterializer;
import io.deephaven.parquet.compress.CompressorAdapter;
import io.deephaven.util.channel.SeekableChannelContext;
import io.deephaven.util.channel.SeekableChannelsProvider;
Expand Down Expand Up @@ -344,8 +345,7 @@ private IntBuffer readKeysFromPageCommon(
final RunLengthBitPackingHybridBufferDecoder rlDecoder,
final RunLengthBitPackingHybridBufferDecoder dlDecoder,
final ValuesReader dataReader) throws IOException {
final Object result = materialize(PageMaterializer.IntFactory, dlDecoder, rlDecoder, dataReader,
nullPlaceholder);
final Object result = materialize(IntMaterializer.Factory, dlDecoder, rlDecoder, dataReader, nullPlaceholder);
if (result instanceof DataWithOffsets) {
keyDest.put((int[]) ((DataWithOffsets) result).materializeResult);
return ((DataWithOffsets) result).offsets;
Expand Down
Loading
Loading