rdblue commented on a change in pull request #1083: URL: https://github.com/apache/iceberg/pull/1083#discussion_r438923582
########## File path: spark/src/main/java/org/apache/iceberg/actions/RewriteDataFilesAction.java ########## @@ -0,0 +1,281 @@ +/* + * 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.actions; + +import java.io.IOException; +import java.util.Collection; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import org.apache.iceberg.CombinedScanTask; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.RewriteFiles; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.encryption.EncryptionManager; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Iterables; +import org.apache.iceberg.relocated.com.google.common.collect.ListMultimap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.relocated.com.google.common.collect.Multimaps; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.relocated.com.google.common.collect.Streams; +import org.apache.iceberg.spark.source.RowDataRewriter; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.StructLikeWrapper; +import org.apache.iceberg.util.TableScanUtil; +import org.apache.iceberg.util.Tasks; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.broadcast.Broadcast; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class RewriteDataFilesAction + extends BaseSnapshotUpdateAction<RewriteDataFilesAction, RewriteDataFilesActionResult> { + + private static final Logger LOG = LoggerFactory.getLogger(RewriteDataFilesAction.class); + + private final JavaSparkContext sparkContext; + private final Table table; + private final FileIO fileIO; + private final EncryptionManager encryptionManager; + private final boolean caseSensitive; + private long targetSizeInBytes; + private int splitLookback; + private long splitOpenFileCost; + + private PartitionSpec spec = null; + private Expression filter; + + RewriteDataFilesAction(SparkSession spark, Table table) { + this.sparkContext = new JavaSparkContext(spark.sparkContext()); + this.table = table; + this.spec = table.spec(); + this.filter = Expressions.alwaysTrue(); + this.caseSensitive = Boolean.parseBoolean(spark.conf().get("spark.sql.caseSensitive", "false")); + + long splitSize = PropertyUtil.propertyAsLong( + table.properties(), + TableProperties.SPLIT_SIZE, + TableProperties.SPLIT_SIZE_DEFAULT); + long targetFileSize = PropertyUtil.propertyAsLong( + table.properties(), + TableProperties.WRITE_TARGET_FILE_SIZE_BYTES, + TableProperties.WRITE_TARGET_FILE_SIZE_BYTES_DEFAULT); + this.targetSizeInBytes = Math.min(splitSize, targetFileSize); Review comment: After thinking about this a bit more, I think I wasn't correct that target write size is a maximum. It's currently used that way in Spark, but the property is "target" and that implies that it is the size files _should_ be, ideally. So Anton is right and that's the size of files we should attempt to create. This also makes sense because it is a `write` property, not a `read` property. I think we should remove the min with split size and just use the table's target size as the default. ---------------------------------------------------------------- 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]
