Jackie-Jiang commented on a change in pull request #6320: URL: https://github.com/apache/incubator-pinot/pull/6320#discussion_r537789457
########## File path: pinot-perf/src/main/java/org/apache/pinot/perf/BenchmarkOffheapBitmapInvertedIndexCreator.java ########## @@ -0,0 +1,105 @@ +/** + * 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.pinot.perf; + +import org.apache.commons.io.FileUtils; +import org.apache.pinot.core.segment.creator.impl.inv.OffHeapBitmapInvertedIndexCreator; +import org.apache.pinot.spi.data.DimensionFieldSpec; +import org.apache.pinot.spi.data.FieldSpec; +import org.openjdk.jmh.annotations.*; +import org.openjdk.jmh.runner.Runner; +import org.openjdk.jmh.runner.options.ChainedOptionsBuilder; +import org.openjdk.jmh.runner.options.OptionsBuilder; + +import java.io.IOException; +import java.nio.file.Files; +import java.nio.file.Path; + +@State(Scope.Benchmark) +public class BenchmarkOffheapBitmapInvertedIndexCreator { Review comment: Please reformat this file to fix the indentation (should be 2 spaces) for this file ########## File path: pinot-core/src/main/java/org/apache/pinot/core/segment/creator/impl/inv/OffHeapBitmapInvertedIndexCreator.java ########## @@ -181,33 +184,45 @@ public void seal() } // Create bitmaps from inverted index buffers and serialize them to file - try (DataOutputStream offsetDataStream = new DataOutputStream( - new BufferedOutputStream(new FileOutputStream(_invertedIndexFile))); - FileOutputStream bitmapFileStream = new FileOutputStream(_invertedIndexFile); - DataOutputStream bitmapDataStream = new DataOutputStream(new BufferedOutputStream(bitmapFileStream))) { - int bitmapOffset = (_cardinality + 1) * Integer.BYTES; - offsetDataStream.writeInt(bitmapOffset); - bitmapFileStream.getChannel().position(bitmapOffset); - + ByteBuffer offsetBuffer = null; + ByteBuffer bitmapBuffer = null; + try (FileChannel channel = new RandomAccessFile(_invertedIndexFile, "rw").getChannel()) { + // map the offsets buffer + int startOfBitmaps = (_cardinality + 1) * Integer.BYTES; + offsetBuffer = channel.map(FileChannel.MapMode.READ_WRITE, 0, startOfBitmaps) + .order(ByteOrder.BIG_ENDIAN); + offsetBuffer.putInt(startOfBitmaps); + bitmapBuffer = channel.map(FileChannel.MapMode.READ_WRITE, startOfBitmaps, Integer.MAX_VALUE - startOfBitmaps) + .order(ByteOrder.LITTLE_ENDIAN); + RoaringBitmapWriter<RoaringBitmap> writer = RoaringBitmapWriter.writer().get(); Review comment: I see your point. We won't create bitmap inverted index if the values are sorted (we have another RLE format), so in most cases, the docIds will spread over all the arrays. But for high cardinality case where each bitmap only contain very few values, pre-allocation might end up allocating too many arrays. So agree with letting it grow automatically. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
