parthchandra commented on a change in pull request #35262: URL: https://github.com/apache/spark/pull/35262#discussion_r805072581
########## File path: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaLengthByteArrayReader.java ########## @@ -0,0 +1,103 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.sql.execution.datasources.parquet; + +import static org.apache.spark.sql.types.DataTypes.IntegerType; + +import java.io.EOFException; +import java.io.IOException; +import java.nio.ByteBuffer; +import org.apache.parquet.bytes.ByteBufferInputStream; +import org.apache.parquet.io.ParquetDecodingException; +import org.apache.spark.memory.MemoryMode; +import org.apache.spark.sql.execution.vectorized.OffHeapColumnVector; +import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector; +import org.apache.spark.sql.execution.vectorized.WritableColumnVector; + +/** + * An implementation of the Parquet DELTA_LENGTH_BYTE_ARRAY decoder that supports the vectorized + * interface. + */ +public class VectorizedDeltaLengthByteArrayReader extends VectorizedReaderBase implements + VectorizedValuesReader { + + private final MemoryMode memoryMode; + private final VectorizedDeltaBinaryPackedReader lengthReader = + new VectorizedDeltaBinaryPackedReader(); + private ByteBufferInputStream in; + private WritableColumnVector lengthsVector; + private int currentRow = 0; + + VectorizedDeltaLengthByteArrayReader(MemoryMode memoryMode) { + this.memoryMode = memoryMode; + } + + @Override + public void initFromPage(int valueCount, ByteBufferInputStream in) throws IOException { + if (memoryMode == MemoryMode.OFF_HEAP) { + lengthsVector = new OffHeapColumnVector(valueCount, IntegerType); + lengthsVector.putInts(0, valueCount, 0); + } else { + lengthsVector = new OnHeapColumnVector(valueCount, IntegerType); + } + lengthReader.initFromPage(valueCount, in); + lengthReader.readIntegers(lengthReader.getTotalValueCount(), lengthsVector, 0); + this.in = in.remainingStream(); + } + + @Override + public void readBinary(int total, WritableColumnVector c, int rowId) { + if (total == 0) { + return; + } + ByteBuffer buffer; + ByteBufferOutputWriter outputWriter; + if (memoryMode == MemoryMode.OFF_HEAP) { + outputWriter = ByteBufferOutputWriter::copyWriteByteBuffer; + } else { + outputWriter = ByteBufferOutputWriter::writeArrayByteBuffer; + } + int length; + for (int i = 0; i < total; i++) { + length = lengthsVector.getInt(rowId + i); Review comment: ☝️ @LuciferYang , @sunchao, should I remove this or not? ########## File path: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java ########## @@ -16,51 +16,121 @@ */ package org.apache.spark.sql.execution.datasources.parquet; +import static org.apache.spark.sql.types.DataTypes.BinaryType; +import static org.apache.spark.sql.types.DataTypes.IntegerType; + import org.apache.parquet.bytes.ByteBufferInputStream; -import org.apache.parquet.column.values.deltastrings.DeltaByteArrayReader; +import org.apache.parquet.column.values.RequiresPreviousReader; +import org.apache.parquet.column.values.ValuesReader; import org.apache.parquet.io.api.Binary; +import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector; import org.apache.spark.sql.execution.vectorized.WritableColumnVector; import java.io.IOException; import java.nio.ByteBuffer; /** - * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the vectorized interface. + * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the vectorized + * interface. */ -public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase { - private final DeltaByteArrayReader deltaByteArrayReader = new DeltaByteArrayReader(); +public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase + implements VectorizedValuesReader, RequiresPreviousReader { + + private final VectorizedDeltaBinaryPackedReader prefixLengthReader = + new VectorizedDeltaBinaryPackedReader(); + private final VectorizedDeltaLengthByteArrayReader suffixReader; + private WritableColumnVector prefixLengthVector; + private WritableColumnVector suffixVector; + private byte[] previous = new byte[0]; + private int currentRow = 0; + + //temporary variable used by getBinary + private final WritableColumnVector binaryValVector; + + VectorizedDeltaByteArrayReader() { + this.suffixReader = new VectorizedDeltaLengthByteArrayReader(); + binaryValVector = new OnHeapColumnVector(1, BinaryType); + } @Override public void initFromPage(int valueCount, ByteBufferInputStream in) throws IOException { - deltaByteArrayReader.initFromPage(valueCount, in); + prefixLengthVector = new OnHeapColumnVector(valueCount, IntegerType); + suffixVector = new OnHeapColumnVector(valueCount, BinaryType); + prefixLengthReader.initFromPage(valueCount, in); + prefixLengthReader.readIntegers(prefixLengthReader.getTotalValueCount(), + prefixLengthVector, 0); + suffixReader.initFromPage(valueCount, in); + suffixReader.readBinary(valueCount, suffixVector, 0); } @Override public Binary readBinary(int len) { - return deltaByteArrayReader.readBytes(); + readValues(1, binaryValVector, 0, ByteBufferOutputWriter::writeArrayByteBuffer); + return Binary.fromConstantByteArray(binaryValVector.getBinary(0)); } - @Override - public void readBinary(int total, WritableColumnVector c, int rowId) { + private void readValues(int total, WritableColumnVector c, int rowId, + ByteBufferOutputWriter outputWriter) { + if (total == 0) { Review comment: Removed ########## File path: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java ########## @@ -16,51 +16,121 @@ */ package org.apache.spark.sql.execution.datasources.parquet; +import static org.apache.spark.sql.types.DataTypes.BinaryType; +import static org.apache.spark.sql.types.DataTypes.IntegerType; + import org.apache.parquet.bytes.ByteBufferInputStream; -import org.apache.parquet.column.values.deltastrings.DeltaByteArrayReader; +import org.apache.parquet.column.values.RequiresPreviousReader; +import org.apache.parquet.column.values.ValuesReader; import org.apache.parquet.io.api.Binary; +import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector; import org.apache.spark.sql.execution.vectorized.WritableColumnVector; import java.io.IOException; import java.nio.ByteBuffer; /** - * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the vectorized interface. + * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the vectorized + * interface. */ -public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase { - private final DeltaByteArrayReader deltaByteArrayReader = new DeltaByteArrayReader(); +public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase + implements VectorizedValuesReader, RequiresPreviousReader { + + private final VectorizedDeltaBinaryPackedReader prefixLengthReader = + new VectorizedDeltaBinaryPackedReader(); + private final VectorizedDeltaLengthByteArrayReader suffixReader; + private WritableColumnVector prefixLengthVector; + private WritableColumnVector suffixVector; + private byte[] previous = new byte[0]; + private int currentRow = 0; + + //temporary variable used by getBinary + private final WritableColumnVector binaryValVector; + + VectorizedDeltaByteArrayReader() { + this.suffixReader = new VectorizedDeltaLengthByteArrayReader(); + binaryValVector = new OnHeapColumnVector(1, BinaryType); + } @Override public void initFromPage(int valueCount, ByteBufferInputStream in) throws IOException { - deltaByteArrayReader.initFromPage(valueCount, in); + prefixLengthVector = new OnHeapColumnVector(valueCount, IntegerType); + suffixVector = new OnHeapColumnVector(valueCount, BinaryType); + prefixLengthReader.initFromPage(valueCount, in); + prefixLengthReader.readIntegers(prefixLengthReader.getTotalValueCount(), + prefixLengthVector, 0); + suffixReader.initFromPage(valueCount, in); + suffixReader.readBinary(valueCount, suffixVector, 0); } @Override public Binary readBinary(int len) { - return deltaByteArrayReader.readBytes(); + readValues(1, binaryValVector, 0, ByteBufferOutputWriter::writeArrayByteBuffer); + return Binary.fromConstantByteArray(binaryValVector.getBinary(0)); } - @Override - public void readBinary(int total, WritableColumnVector c, int rowId) { + private void readValues(int total, WritableColumnVector c, int rowId, + ByteBufferOutputWriter outputWriter) { + if (total == 0) { Review comment: Also, I'm running the benchmarks again. Will update the results. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
