aokolnychyi commented on a change in pull request #2472: URL: https://github.com/apache/iceberg/pull/2472#discussion_r615124403
########## File path: spark3/src/main/java/org/apache/iceberg/spark/FileScanTaskSetManager.java ########## @@ -0,0 +1,64 @@ +/* + * 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; + +import java.util.List; +import java.util.Map; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.util.Pair; + +public class FileScanTaskSetManager { + + private static final FileScanTaskSetManager INSTANCE = new FileScanTaskSetManager(); + + private final Map<Pair<String, String>, List<FileScanTask>> tasksMap = Maps.newConcurrentMap(); + + private FileScanTaskSetManager() { + } + + public static FileScanTaskSetManager get() { + return INSTANCE; + } + + public void stageTasks(Table table, String setID, List<FileScanTask> tasks) { + Pair<String, String> id = toID(table, setID); + tasksMap.put(id, tasks); + } + + public List<FileScanTask> fetchTasks(Table table, String setID) { + Pair<String, String> id = toID(table, setID); + return tasksMap.get(id); Review comment: Updated. ########## File path: spark3/src/main/java/org/apache/iceberg/spark/source/SparkFilesScan.java ########## @@ -0,0 +1,123 @@ +/* + * 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.source; + +import java.util.List; +import java.util.Map; +import java.util.Objects; +import org.apache.iceberg.CombinedScanTask; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Table; +import org.apache.iceberg.encryption.EncryptionManager; +import org.apache.iceberg.io.CloseableIterable; +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.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.FileScanTaskSetManager; +import org.apache.iceberg.spark.Spark3Util; +import org.apache.iceberg.spark.SparkReadOptions; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.TableScanUtil; +import org.apache.spark.broadcast.Broadcast; +import org.apache.spark.sql.util.CaseInsensitiveStringMap; + +import static org.apache.iceberg.TableProperties.SPLIT_LOOKBACK; +import static org.apache.iceberg.TableProperties.SPLIT_LOOKBACK_DEFAULT; +import static org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST; +import static org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST_DEFAULT; +import static org.apache.iceberg.TableProperties.SPLIT_SIZE; +import static org.apache.iceberg.TableProperties.SPLIT_SIZE_DEFAULT; + +class SparkFilesScan extends SparkBatchScan { + private final String taskSetID; + private final Long splitSize; + private final Integer splitLookback; + private final Long splitOpenFileCost; + + private List<CombinedScanTask> tasks = null; // lazy cache of tasks + + SparkFilesScan(Table table, Broadcast<FileIO> io, Broadcast<EncryptionManager> encryption, + boolean caseSensitive, CaseInsensitiveStringMap options) { + super(table, io, encryption, caseSensitive, table.schema(), ImmutableList.of(), options); + + this.taskSetID = options.get(SparkReadOptions.FILE_SCAN_TASK_SET_ID); + + Map<String, String> props = table.properties(); + + long tableSplitSize = PropertyUtil.propertyAsLong(props, SPLIT_SIZE, SPLIT_SIZE_DEFAULT); + this.splitSize = Spark3Util.propertyAsLong(options, SparkReadOptions.SPLIT_SIZE, tableSplitSize); + + int tableSplitLookback = PropertyUtil.propertyAsInt(props, SPLIT_LOOKBACK, SPLIT_LOOKBACK_DEFAULT); + this.splitLookback = Spark3Util.propertyAsInt(options, SparkReadOptions.LOOKBACK, tableSplitLookback); + + long tableOpenFileCost = PropertyUtil.propertyAsLong(props, SPLIT_OPEN_FILE_COST, SPLIT_OPEN_FILE_COST_DEFAULT); + this.splitOpenFileCost = Spark3Util.propertyAsLong(options, SparkReadOptions.FILE_OPEN_COST, tableOpenFileCost); + } + + @Override + protected List<CombinedScanTask> tasks() { + if (tasks == null) { + FileScanTaskSetManager taskSetManager = FileScanTaskSetManager.get(); + List<FileScanTask> files = taskSetManager.fetchTasks(table(), taskSetID); + Preconditions.checkArgument(files != null, "No file tasks for table %s and set %s", table(), taskSetID); Review comment: Fixed. ########## File path: spark3/src/test/java/org/apache/iceberg/spark/source/TestSparkFilesScan.java ########## @@ -0,0 +1,84 @@ +/* + * 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.source; + +import java.io.IOException; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.Table; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Iterables; +import org.apache.iceberg.spark.FileScanTaskSetManager; +import org.apache.iceberg.spark.SparkCatalogTestBase; +import org.apache.iceberg.spark.SparkReadOptions; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.junit.After; +import org.junit.Assert; +import org.junit.Test; + +public class TestSparkFilesScan extends SparkCatalogTestBase { + + public TestSparkFilesScan(String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @After + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + } + + @Test + public void testTaskSetLoading() throws NoSuchTableException, IOException { Review comment: Added. -- 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]
