npawar commented on a change in pull request #6718: URL: https://github.com/apache/incubator-pinot/pull/6718#discussion_r603615312
########## File path: pinot-plugins/pinot-segment-writer/pinot-segment-writer-file-based/src/main/java/org/apache/pinot/plugin/segmentwriter/filebased/FileBasedSegmentWriter.java ########## @@ -0,0 +1,193 @@ +/** + * 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.plugin.segmentwriter.filebased; + +import com.google.common.base.Preconditions; +import com.google.common.collect.Lists; +import java.io.File; +import java.io.IOException; +import java.net.URI; +import java.nio.file.Files; +import java.nio.file.Paths; +import java.util.HashMap; +import java.util.Map; +import java.util.Set; +import org.apache.avro.file.DataFileWriter; +import org.apache.avro.generic.GenericData; +import org.apache.avro.generic.GenericDatumWriter; +import org.apache.commons.collections.CollectionUtils; +import org.apache.commons.io.FileUtils; +import org.apache.commons.lang3.StringUtils; +import org.apache.pinot.common.utils.TarGzCompressionUtils; +import org.apache.pinot.core.data.recordtransformer.CompositeTransformer; +import org.apache.pinot.core.data.recordtransformer.RecordTransformer; +import org.apache.pinot.core.indexsegment.generator.SegmentGeneratorConfig; +import org.apache.pinot.core.util.IngestionUtils; +import org.apache.pinot.core.util.SegmentProcessorAvroUtils; +import org.apache.pinot.spi.config.table.TableConfig; +import org.apache.pinot.spi.config.table.ingestion.BatchIngestionConfig; +import org.apache.pinot.spi.data.Schema; +import org.apache.pinot.spi.data.readers.FileFormat; +import org.apache.pinot.spi.data.readers.GenericRow; +import org.apache.pinot.spi.ingestion.batch.BatchConfig; +import org.apache.pinot.spi.ingestion.batch.BatchConfigProperties; +import org.apache.pinot.spi.ingestion.batch.spec.Constants; +import org.apache.pinot.spi.ingestion.segment.writer.SegmentWriter; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + + +/** + * A {@link SegmentWriter} implementation that uses a local file as a buffer to collect {@link GenericRow}. + * The {@link GenericRow} are written to the buffer as AVRO records. + */ +public class FileBasedSegmentWriter implements SegmentWriter { + + private static final Logger LOGGER = LoggerFactory.getLogger(FileBasedSegmentWriter.class); + private static final FileFormat BUFFER_FILE_FORMAT = FileFormat.AVRO; + + private TableConfig _tableConfig; + private String _tableNameWithType; + private BatchIngestionConfig _batchIngestionConfig; + private BatchConfig _batchConfig; + private String _outputDirURI; + private Schema _schema; + private Set<String> _fieldsToRead; + private RecordTransformer _recordTransformer; + + private File _stagingDir; + private File _bufferFile; Review comment: I dont have any numbers as of now. I plan to add one impl using the new IntermediateSegmentRecordReader. I anticipate the ingestion speed to be faster, as records will be kept in memory similar to realtime, and we will not be doing any file writes. But you'll have to make sure you have offheap memory available to hold all the records, in addition to the memory required for building segment (which would be same in both cases). Will do some perf comparison once i have that. -- 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]
