thomasmueller commented on code in PR #728: URL: https://github.com/apache/jackrabbit-oak/pull/728#discussion_r989758645
########## oak-run/src/main/java/org/apache/jackrabbit/oak/run/DataStoreCopyCommand.java: ########## @@ -0,0 +1,162 @@ +/* + * 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.jackrabbit.oak.run; + +import joptsimple.OptionParser; +import joptsimple.OptionSet; +import joptsimple.OptionSpec; +import joptsimple.OptionSpecBuilder; +import org.apache.jackrabbit.oak.commons.IOUtils; +import org.apache.jackrabbit.oak.run.commons.Command; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.File; +import java.nio.charset.StandardCharsets; +import java.nio.file.Files; +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import java.util.concurrent.TimeUnit; +import java.util.stream.Collectors; + +import static com.google.common.base.StandardSystemProperty.FILE_SEPARATOR; + +/** + * Command to concurrently download blobs from an azure datastore using sas token authentication. + * <p> + * Blobs are stored in a specific folder following the datastore structure format. + */ +public class DataStoreCopyCommand implements Command { + + private static final Logger LOG = LoggerFactory.getLogger(DataStoreCopyCommand.class); + + private String sourceRepo; + private String includePath; + private File fileIncludePath; + private String sasToken; + private String outDir; + private int concurrency; + + @Override + public void execute(String... args) throws Exception { + parseCommandLineParams(args); + + List<String> ids; + if (fileIncludePath != null) { + if (fileIncludePath.isDirectory() || !fileIncludePath.exists()) { + throw new IllegalArgumentException("file-include-path must be a valid file"); + } + ids = org.apache.commons.io.IOUtils.readLines(Files.newInputStream(fileIncludePath.toPath()), StandardCharsets.UTF_8); + } else { + ids = Arrays.stream(includePath.split(";")).collect(Collectors.toList()); + } + if (ids.isEmpty()) { + throw new IllegalArgumentException("Blob ids must be specified"); + } + + try (Downloader downloader = new Downloader(concurrency)) { + long start = System.currentTimeMillis(); + List<Downloader.ItemResponse> responses = downloader.download(ids.stream().map(id -> { Review Comment: Wouldn't that have the downside that you can't show the progress, in number of bytes (remaining)? ########## oak-run/src/main/java/org/apache/jackrabbit/oak/run/Downloader.java: ########## @@ -0,0 +1,142 @@ +/* + * 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.jackrabbit.oak.run; + +import com.google.common.util.concurrent.ThreadFactoryBuilder; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.Closeable; +import java.io.File; +import java.io.FileOutputStream; +import java.io.IOException; +import java.net.URL; +import java.nio.channels.Channels; +import java.nio.channels.ReadableByteChannel; +import java.util.List; +import java.util.concurrent.Callable; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.LinkedBlockingQueue; +import java.util.concurrent.ThreadPoolExecutor; +import java.util.concurrent.TimeUnit; +import java.util.stream.Collectors; + +/** + * Generic concurrent file downloader which uses Java NIO channels to potentially leverage OS internal optimizations. + */ +public class Downloader implements Closeable { + + private static final Logger LOG = LoggerFactory.getLogger(Downloader.class); + + private final ExecutorService executorService; + + public Downloader(int concurrency) { + LOG.info("Initializing Downloader with max number of concurrent requests={}", concurrency); + this.executorService = new ThreadPoolExecutor( + (int) Math.ceil(concurrency * .1), concurrency, 60L, TimeUnit.SECONDS, + new LinkedBlockingQueue<>(), + new ThreadFactoryBuilder() + .setNameFormat("downloader-%d") + .setDaemon(true) + .build() + ); + } + + public List<ItemResponse> download(List<Item> items) { + LOG.debug("Preparing to download {} items.\n{}", items.size(), items); + try { + return executorService + .invokeAll(items.stream().map(DownloadWorker::new).collect(Collectors.toList())) + .stream() + .map(itemResponseFuture -> { + try { + return itemResponseFuture.get(); + } catch (InterruptedException | ExecutionException e) { + throw new RuntimeException(e); + } + }) + .collect(Collectors.toList()); + } catch (InterruptedException e) { + throw new RuntimeException(e); + } + } + + @Override + public void close() throws IOException { + executorService.shutdown(); + } + + public static class Item { + public String source; + public String destination; + + @Override + public String toString() { + return "Item{" + + "source='" + source + '\'' + + ", destination='" + destination + '\'' + + '}'; + } + } + + public static class ItemResponse { + public final Item item; + public boolean failed; + public long size; + public long time; + public Throwable throwable; + + public ItemResponse(Item item) { + this.item = item; + } + } + + private static class DownloadWorker implements Callable<ItemResponse> { + + private final Item item; + + DownloadWorker(Item item) { + this.item = item; + } + + @Override + public ItemResponse call() { + ItemResponse response = new ItemResponse(item); + long t0 = System.currentTimeMillis(); + try { + URL sourceUrl = new URL(item.source); + File destinationFile = new File(item.destination); + destinationFile.getParentFile().mkdirs(); + try (ReadableByteChannel byteChannel = Channels.newChannel(sourceUrl.openStream()); + FileOutputStream outputStream = new FileOutputStream(destinationFile)) { + response.size = outputStream.getChannel() + .transferFrom(byteChannel, 0, Long.MAX_VALUE); Review Comment: If I'm not mistaken (but I didn't check), transferFromArbitraryChannel does already use buffers... so I see the usage of transferFrom to be a convenience... But I might be wrong. -- 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]
