sachouche commented on a change in pull request #1330: DRILL-6147: Adding Columnar Parquet Batch Sizing functionality URL: https://github.com/apache/drill/pull/1330#discussion_r199036653
########## File path: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/columnreaders/batchsizing/RecordBatchSizerManager.java ########## @@ -0,0 +1,657 @@ +/* + * 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.drill.exec.store.parquet.columnreaders.batchsizing; + +import java.util.ArrayList; +import java.util.List; +import java.util.Map; +import org.apache.drill.common.map.CaseInsensitiveMap; +import org.apache.drill.common.types.TypeProtos.MajorType; +import org.apache.drill.exec.ExecConstants; +import org.apache.drill.exec.exception.OutOfMemoryException; +import org.apache.drill.exec.record.MaterializedField; +import org.apache.drill.exec.server.options.OptionManager; +import org.apache.drill.exec.store.parquet.columnreaders.ParquetColumnMetadata; +import org.apache.drill.exec.store.parquet.columnreaders.ParquetSchema; +import org.apache.drill.exec.store.parquet.columnreaders.VarLenColumnBulkInput; +import org.apache.drill.exec.store.parquet.columnreaders.batchsizing.RecordBatchOverflow.FieldOverflowDefinition; +import org.apache.drill.exec.vector.AllocationHelper; +import org.apache.drill.exec.vector.ValueVector; + +/** + * This class is tasked with managing all aspects of flat Parquet reader record batch sizing logic. + * Currently a record batch size is constrained with two parameters: Number of rows and Memory usage. + */ +public final class RecordBatchSizerManager { + private static final org.slf4j.Logger logger = org.slf4j.LoggerFactory.getLogger(RecordBatchSizerManager.class); + public static final String BATCH_STATS_PREFIX = "BATCH_STATS"; + + /** Minimum column memory size */ + private static final int MIN_COLUMN_MEMORY_SZ = VarLenColumnBulkInput.getMinVLColumnMemorySize(); + /** Default memory per batch */ + private static final int DEFAULT_MEMORY_SZ_PER_BATCH = 16 * 1024 * 1024; + /** Default records per batch */ + private static final int DEFAULT_RECORDS_PER_BATCH = 32 * 1024 -1; Review comment: The default values have been added previously before we agreed on a common operator configuration. I have removed these default values. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
