gvprathyusha6 commented on code in PR #8248: URL: https://github.com/apache/hbase/pull/8248#discussion_r3475903912
########## hbase-mapreduce/src/main/java/org/apache/hadoop/hbase/util/MapreduceHFileArchiver.java: ########## @@ -0,0 +1,598 @@ +/* + * 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.hadoop.hbase.util; + +import java.io.FileNotFoundException; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collection; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Queue; +import java.util.concurrent.ConcurrentLinkedQueue; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.Future; +import java.util.concurrent.ThreadFactory; +import java.util.concurrent.ThreadPoolExecutor; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.atomic.AtomicInteger; +import java.util.function.Function; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.fs.PathFilter; +import org.apache.hadoop.hbase.backup.FailedArchiveException; +import org.apache.hadoop.hbase.client.RegionInfo; +import org.apache.hadoop.hbase.snapshot.RestoreSnapshotArchiver; +import org.apache.yetus.audience.InterfaceAudience; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import org.apache.hbase.thirdparty.com.google.common.base.Preconditions; + +/** + * MapReduce-local archiver used by {@link + * org.apache.hadoop.hbase.mapreduce.MapreduceRestoreSnapshotHelper}. It mirrors the server-side + * {@code HFileArchiver} but lives in the MapReduce module so the snapshot-scanning path can be + * evolved independently. It is injected into the shared {@link + * org.apache.hadoop.hbase.snapshot.RestoreSnapshotHelper} restore/clone logic via {@link + * RestoreSnapshotArchiver}. + */ [email protected] +public class MapreduceHFileArchiver implements RestoreSnapshotArchiver { + + private static final Logger LOG = LoggerFactory.getLogger(MapreduceHFileArchiver.class); + private static final String SEPARATOR = "."; + + /** Number of retries in case of fs operation failure */ + private static final int DEFAULT_RETRIES_NUMBER = 3; + + private static final Function<File, Path> FUNC_FILE_TO_PATH = new Function<File, Path>() { + @Override + public Path apply(File file) { + return file == null ? null : file.getPath(); + } + }; + + /** Returns True if the Region exits in the filesystem. */ + public static boolean exists(Configuration conf, FileSystem fs, RegionInfo info) + throws IOException { + Path rootDir = CommonFSUtils.getRootDir(conf); Review Comment: We should avoid getting root directory from CommonFSUtils right? -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
