RussellSpitzer commented on a change in pull request #2591: URL: https://github.com/apache/iceberg/pull/2591#discussion_r632247863
########## File path: spark3/src/main/java/org/apache/iceberg/spark/actions/rewrite/Spark3BinPackStrategy.java ########## @@ -0,0 +1,79 @@ +/* + * 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.rewrite; + +import java.util.List; +import java.util.Set; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.BinPackStrategy; +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.SparkReadOptions; +import org.apache.iceberg.spark.SparkWriteOptions; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; + +public class Spark3BinPackStrategy extends BinPackStrategy { + private final Table table; + private final SparkSession spark; + private final FileScanTaskSetManager manager = FileScanTaskSetManager.get(); + + public Spark3BinPackStrategy(Table table, SparkSession spark) { + this.table = table; + this.spark = spark; + } + + + @Override + public Table table() { + return table; + } + + @Override + public Set<DataFile> rewriteFiles(String setId, List<FileScanTask> filesToRewrite) { + manager.stageTasks(table, setId, filesToRewrite); + + // read and pack original 4 files into 2 splits + Dataset<Row> scanDF = spark.read().format("iceberg") + .option(SparkReadOptions.FILE_SCAN_TASK_SET_ID, setId) + .option(SparkReadOptions.SPLIT_SIZE, Long.toString(targetFileSize())) + .option(SparkReadOptions.FILE_OPEN_COST, "0") + .load(table.name()); + + // write the packed data into new files where each split becomes a new file + try { + scanDF.write() + .format("iceberg") + .option(SparkWriteOptions.REWRITTEN_FILE_SCAN_TASK_SET_ID, setId) + .mode("append") + .save(table.name()); + } catch (Exception e) { + throw new RuntimeException(e); + } + + FileRewriteCoordinator rewriteCoordinator = FileRewriteCoordinator.get(); + return rewriteCoordinator.fetchNewDataFiles(table, ImmutableSet.of(setId)); Review comment: Hmm I think that's true, it does mean i have to handle cleanup slightly differently in the action itself. The case where we don't have partial progress enabled but do have multiple file groups being committed can lead to a situation where several sets of files that have been successfully rewritten but since the commit is invalid we need to clear them out. It's late so we can probably talk about this tomorrow after I slept a bit. -- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
