sarvekshayr commented on code in PR #10813: URL: https://github.com/apache/ozone/pull/10813#discussion_r3620644804
########## hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/export/ContainerExportManager.java: ########## @@ -0,0 +1,647 @@ +/* + * 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.hdds.scm.container.export; + +import static org.apache.hadoop.hdds.scm.container.export.ContainerExportLimits.DEFAULT_PAGE_SIZE; +import static org.apache.hadoop.hdds.scm.container.export.ContainerExportLimits.DEFAULT_SHARD_SIZE; +import static org.apache.hadoop.hdds.scm.container.export.ContainerExportLimits.EXPORT_SUBDIR; +import static org.apache.hadoop.hdds.scm.container.export.ContainerExportLimits.MAX_PAGE_SIZE; +import static org.apache.hadoop.hdds.scm.container.export.ContainerExportLimits.MAX_SHARD_SIZE; + +import java.io.BufferedWriter; +import java.io.File; +import java.io.IOException; +import java.nio.charset.StandardCharsets; +import java.nio.file.Files; +import java.nio.file.Path; +import java.nio.file.Paths; +import java.time.Instant; +import java.time.ZoneOffset; +import java.time.format.DateTimeFormatter; +import java.util.ArrayList; +import java.util.Comparator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.concurrent.ConcurrentHashMap; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.Executors; +import java.util.concurrent.Future; +import java.util.concurrent.TimeUnit; +import java.util.function.BooleanSupplier; +import java.util.stream.Collectors; +import org.apache.commons.io.FileUtils; +import org.apache.hadoop.hdds.conf.OzoneConfiguration; +import org.apache.hadoop.hdds.protocol.proto.HddsProtos.LifeCycleState; +import org.apache.hadoop.hdds.scm.container.ContainerHealthState; +import org.apache.hadoop.hdds.scm.container.ContainerID; +import org.apache.hadoop.hdds.scm.container.ContainerManager; +import org.apache.hadoop.hdds.server.ServerUtils; +import org.apache.hadoop.hdds.utils.Archiver; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * Manages asynchronous container ID export jobs on the SCM leader. + * + * <p>Health filters read {@link org.apache.hadoop.hdds.scm.container.ContainerInfo#getHealthState()} + * as last written by Replication Manager; they are not recomputed during export and may be stale + * if RM has not yet evaluated a container. + * + * <p>Job status is kept in memory only. On SCM restart or leader failover, in-flight jobs are lost + * and the operator must re-submit on the new leader. Completed TAR files remain on disk until + * manually deleted. On startup, incomplete work ({@code {jobId}.inprogress} markers, UUID work + * directories, and matching partial TAR files) is removed. + */ +public class ContainerExportManager { + + private static final Logger LOG = LoggerFactory.getLogger(ContainerExportManager.class); + + private static final String INPROGRESS_MARKER_SUFFIX = ".inprogress"; + + //TODO: make ozone.scm.container.export.max.terminal.jobs configurable. + private static final int DEFAULT_MAX_TERMINAL_JOBS = 10; + + private static final DateTimeFormatter METADATA_TIMESTAMP_FORMAT = + DateTimeFormatter.ofPattern("yyyy-MM-dd'T'HH:mm:ss'Z'").withZone(ZoneOffset.UTC); + private static final DateTimeFormatter FILENAME_TIMESTAMP_FORMAT = + DateTimeFormatter.ofPattern("yyyyMMdd'T'HHmmss'Z'").withZone(ZoneOffset.UTC); + + private final Map<String, ExportJob> jobTracker = new ConcurrentHashMap<>(); + private final ExecutorService workerPool; + private final Map<String, Future<?>> runningTasks = new ConcurrentHashMap<>(); Review Comment: Removed the map. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
