RussellSpitzer commented on a change in pull request #2829: URL: https://github.com/apache/iceberg/pull/2829#discussion_r731237603
########## File path: spark3/src/main/java/org/apache/iceberg/spark/actions/Spark3SortStrategy.java ########## @@ -0,0 +1,163 @@ +/* + * 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.iceberg.spark.actions; + +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.UUID; +import java.util.stream.Stream; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.RewriteDataFiles; +import org.apache.iceberg.actions.RewriteStrategy; +import org.apache.iceberg.actions.SortStrategy; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.spark.FileRewriteCoordinator; +import org.apache.iceberg.spark.FileScanTaskSetManager; +import org.apache.iceberg.spark.Spark3Util; +import org.apache.iceberg.spark.SparkReadOptions; +import org.apache.iceberg.spark.SparkWriteOptions; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan; +import org.apache.spark.sql.catalyst.utils.DistributionAndOrderingUtils$; +import org.apache.spark.sql.connector.iceberg.distributions.Distribution; +import org.apache.spark.sql.connector.iceberg.distributions.Distributions; +import org.apache.spark.sql.connector.iceberg.expressions.SortOrder; +import org.apache.spark.sql.internal.SQLConf; + +public class Spark3SortStrategy extends SortStrategy { + + /** + * The number of shuffle partitions and consequently the number of output files + * created by the Spark Sort is based on the size of the input data files used + * in this rewrite operation. Due to compression, the disk file sizes may not + * accurately represent the size of files in the output. This parameter lets + * the user adjust the file size used for estimating actual output data size. A + * factor greater than 1.0 would generate more files than we would expect based + * on the on-disk file size. A value less than 1.0 would create fewer files than + * we would expect due to the on-disk size. + */ + public static final String COMPRESSION_FACTOR = "compression-factor"; + + public static final String SHUFFLE_TASKS_PER_FILE = "shuffle-tasks-per-file"; + + private final Table table; + private final SparkSession spark; + private final FileScanTaskSetManager manager = FileScanTaskSetManager.get(); + private final FileRewriteCoordinator rewriteCoordinator = FileRewriteCoordinator.get(); + + private double sizeEstimateMultiple; + + public Spark3SortStrategy(Table table, SparkSession spark) { + this.table = table; + this.spark = spark; + } + + @Override + public Table table() { + return table; + } + + @Override + public Set<String> validOptions() { + return ImmutableSet.<String>builder() + .addAll(super.validOptions()) + .add(COMPRESSION_FACTOR) + .add(SHUFFLE_TASKS_PER_FILE) + .build(); + } + + @Override + public RewriteStrategy options(Map<String, String> options) { + sizeEstimateMultiple = PropertyUtil.propertyAsDouble(options, + COMPRESSION_FACTOR, + 1.0); + + Preconditions.checkArgument(sizeEstimateMultiple > 0, + "Invalid compression factor: %s (not positive)", sizeEstimateMultiple); + + return super.options(options); + } + + @Override + public Set<DataFile> rewriteFiles(List<FileScanTask> filesToRewrite) { + String groupID = UUID.randomUUID().toString(); + boolean requiresRepartition = !filesToRewrite.get(0).spec().equals(table.spec()); + SortOrder[] ordering = Spark3Util.convert(sortOrder()); + Distribution distribution; + + if (requiresRepartition) { + distribution = Spark3Util.buildRequiredDistribution(table); + ordering = Stream.concat( + Arrays.stream(Spark3Util.buildRequiredOrdering(distribution, table())), Review comment: Good call, refactored this -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
