aokolnychyi commented on a change in pull request #2500:
URL: https://github.com/apache/iceberg/pull/2500#discussion_r617043226



##########
File path: 
spark3/src/main/java/org/apache/iceberg/spark/FileRewriteCoordinator.java
##########
@@ -0,0 +1,169 @@
+/*
+ * 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 java.util.Set;
+import java.util.concurrent.locks.Lock;
+import java.util.concurrent.locks.ReentrantLock;
+import org.apache.iceberg.DataFile;
+import org.apache.iceberg.FileScanTask;
+import org.apache.iceberg.HasTableOperations;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.TableOperations;
+import org.apache.iceberg.exceptions.ValidationException;
+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.ImmutableSet;
+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.Sets;
+import org.apache.iceberg.util.Pair;
+import org.apache.iceberg.util.Tasks;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+public class FileRewriteCoordinator {
+
+  private static final Logger LOG = 
LoggerFactory.getLogger(FileRewriteCoordinator.class);
+  private static final FileRewriteCoordinator INSTANCE = new 
FileRewriteCoordinator();
+
+  private final Map<String, Lock> lockMap = Maps.newConcurrentMap();
+  private final Map<Pair<String, String>, Set<DataFile>> resultMap = 
Maps.newConcurrentMap();
+
+  private FileRewriteCoordinator() {
+  }
+
+  public static FileRewriteCoordinator get() {
+    return INSTANCE;
+  }
+
+  public void stageRewrite(Table table, String fileSetID, Set<DataFile> 
newDataFiles) {
+    Preconditions.checkArgument(newDataFiles != null && newDataFiles.size() > 
0, "Cannot stage null or empty files");
+    LOG.info("Staging results of rewriting file set {} for table {}", 
fileSetID, table);
+    Pair<String, String> id = toID(table, fileSetID);
+    resultMap.put(id, newDataFiles);
+  }
+
+  public void commitRewrite(Table table, String fileSetID) {
+    commitRewrite(table, ImmutableSet.of(fileSetID));
+  }
+
+  public void commitRewrite(Table table, Set<String> fileSetIDs) {
+    LOG.info("Committing rewrite of file sets {} for table {}", fileSetIDs, 
table);
+
+    Set<DataFile> rewrittenDataFiles = fetchRewrittenDataFiles(table, 
fileSetIDs);
+    Set<DataFile> newDataFiles = fetchNewDataFiles(table, fileSetIDs);
+
+    String tableUUID = tableUUID(table);
+    Lock tableLock = lockMap.computeIfAbsent(tableUUID, uuid -> new 
ReentrantLock());
+
+    try {
+      LOG.info("Locking table {} to commit rewrite of file sets {}", table, 
fileSetIDs);

Review comment:
       I guess it now depends on how we are going to issue commits from the 
action if the user allows partial progress and we commit one chunk at a time. 
If that's going to happen from each thread, then we will need to sync. If we 
just add the rewritten file set ID to the queue from each thread and 
synchronize it somewhere else, then this can be removed.




-- 
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]

Reply via email to