Zakelly commented on code in PR #22590: URL: https://github.com/apache/flink/pull/22590#discussion_r1201504784
########## flink-runtime/src/main/java/org/apache/flink/runtime/checkpoint/filemerging/FileMergingSnapshotManagerBase.java: ########## @@ -0,0 +1,270 @@ +/* + * 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.flink.runtime.checkpoint.filemerging; + +import org.apache.flink.core.fs.EntropyInjector; +import org.apache.flink.core.fs.FSDataOutputStream; +import org.apache.flink.core.fs.FileSystem; +import org.apache.flink.core.fs.OutputStreamAndPath; +import org.apache.flink.core.fs.Path; +import org.apache.flink.runtime.checkpoint.filemerging.FileMergingCheckpointUtils.SnapshotFileSystemInfo; +import org.apache.flink.runtime.checkpoint.filemerging.LogicalFile.LogicalFileId; +import org.apache.flink.runtime.state.CheckpointedStateScope; +import org.apache.flink.util.Preconditions; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import javax.annotation.Nonnull; + +import java.io.IOException; +import java.io.UncheckedIOException; +import java.util.Map; +import java.util.UUID; +import java.util.concurrent.ConcurrentHashMap; +import java.util.concurrent.Executor; + +/** Base implementation of {@link FileMergingSnapshotManager}. */ +public abstract class FileMergingSnapshotManagerBase implements FileMergingSnapshotManager { + + private static final Logger LOG = LoggerFactory.getLogger(FileMergingSnapshotManager.class); + + private final String id; + + protected final Executor ioExecutor; + + // file system and directories + protected FileSystem fs; + protected Path checkpointDir; + protected Path sharedStateDir; + protected Path taskOwnedStateDir; + + protected int writeBufferSize; + private boolean fileSystemInitiated = false; + + protected boolean syncAfterClosingLogicalFile; + + protected PhysicalFile.PhysicalFileDeleter physicalFileDeleter = this::deletePhysicalFile; + + private final Map<SubtaskKey, Path> managedSharedStateDir = new ConcurrentHashMap<>(); + + protected Path managedExclusiveStateDir; + + public FileMergingSnapshotManagerBase(String id, Executor ioExecutor) { + this.id = id; + this.ioExecutor = ioExecutor; + } + + @Override + public void initFileSystem(SnapshotFileSystemInfo fileSystemInfo) throws IOException { + initFileSystem( + fileSystemInfo.fs, + fileSystemInfo.checkpointBaseDirectory, + fileSystemInfo.sharedStateDirectory, + fileSystemInfo.taskOwnedStateDirectory); + } + + @Override + public void addSubtask(SubtaskKey subtaskKey) { + try { + String managedDirName = subtaskKey.getManagedDirName(); + Path managedPath = new Path(sharedStateDir, managedDirName); + fs.mkdirs(managedPath); + managedSharedStateDir.put(subtaskKey, managedPath); Review Comment: Good point. I add de-duplication logic as well as checking if the directory exists in the file system. -- 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: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
