Github user uce commented on a diff in the pull request: https://github.com/apache/flink/pull/3460#discussion_r106903661 --- Diff: flink-runtime-web/src/main/java/org/apache/flink/runtime/webmonitor/history/HistoryServerArchiveFetcher.java --- @@ -0,0 +1,259 @@ +/* + * 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.webmonitor.history; + +import com.fasterxml.jackson.core.JsonFactory; +import com.fasterxml.jackson.core.JsonGenerator; +import com.fasterxml.jackson.databind.JsonNode; +import com.fasterxml.jackson.databind.ObjectMapper; +import org.apache.flink.api.common.JobID; +import org.apache.flink.configuration.HistoryServerOptions; +import org.apache.flink.core.fs.FileStatus; +import org.apache.flink.core.fs.FileSystem; +import org.apache.flink.core.fs.Path; +import org.apache.flink.runtime.filecache.FileCache; +import org.apache.flink.runtime.history.FsJobArchivist; +import org.apache.flink.runtime.util.ExecutorThreadFactory; +import org.apache.flink.runtime.webmonitor.handlers.CurrentJobsOverviewHandler; +import org.apache.flink.util.FileUtils; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.File; +import java.io.FileWriter; +import java.io.IOException; +import java.nio.file.FileAlreadyExistsException; +import java.nio.file.Files; +import java.nio.file.NoSuchFileException; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.TimerTask; +import java.util.concurrent.Executors; +import java.util.concurrent.ScheduledExecutorService; +import java.util.concurrent.TimeUnit; + +/** + * This class is used by the {@link HistoryServer} to fetch the job archives that are located at + * {@link HistoryServerOptions#HISTORY_SERVER_DIRS}. The directories are polled in regular intervals, defined + * by {@link HistoryServerOptions#HISTORY_SERVER_REFRESH_INTERVAL}. + * + * The archives are first copied into a temporary directory in {@link HistoryServerOptions#HISTORY_SERVER_WEB_DIR} and + * then expanded. The resulting file structure is analog to the REST API defined in the WebRuntimeMonitor. + */ +public class HistoryServerArchiveFetcher { + + private static final Logger LOG = LoggerFactory.getLogger(HistoryServerArchiveFetcher.class); + + private static final JsonFactory jacksonFactory = new JsonFactory(); + private static final ObjectMapper mapper = new ObjectMapper(); + + private final ScheduledExecutorService executor = Executors.newSingleThreadScheduledExecutor( + new ExecutorThreadFactory("Flink-HistoryServer-ArchiveFetcher")); + private final JobArchiveFetcherTask fetcherTask; + private final long refreshIntervalMillis; + + HistoryServerArchiveFetcher(long refreshIntervalMillis, List<HistoryServer.RefreshLocation> refreshDirs, File webDir) { + this.refreshIntervalMillis = refreshIntervalMillis; + this.fetcherTask = new JobArchiveFetcherTask(refreshDirs, webDir); + if (LOG.isInfoEnabled()) { + for (HistoryServer.RefreshLocation refreshDir : refreshDirs) { + LOG.info("Monitoring directory {} for archived jobs.", refreshDir.getPath()); + } + } + } + + void start() { + executor.scheduleWithFixedDelay(fetcherTask, 0, refreshIntervalMillis, TimeUnit.MILLISECONDS); + } + + void stop() { + executor.shutdown(); + + try { + if (!executor.awaitTermination(1, TimeUnit.SECONDS)) { + executor.shutdownNow(); + } + } catch (InterruptedException ignored) { + executor.shutdownNow(); + } + } + + /** + * {@link TimerTask} that polls the directories configured as {@link HistoryServerOptions#HISTORY_SERVER_DIRS} for + * new job archives. + */ + static class JobArchiveFetcherTask extends TimerTask { + private final List<HistoryServer.RefreshLocation> refreshDirs; + /** Map containing the JobID of all fetched jobs and the refreshDir from with they originate. */ + private final Map<String, Path> cachedArchives; + private final File webDir; + private final File webTmpDir; + private final File webJobDir; + private final File webOverviewDir; + + private static final String JSON_FILE_ENDING = ".json"; + + JobArchiveFetcherTask(List<HistoryServer.RefreshLocation> refreshDirs, File webDir) { + this.refreshDirs = refreshDirs; + this.cachedArchives = new HashMap<>(); + this.webDir = webDir; + this.webTmpDir = new File(webDir, "tmp"); + webTmpDir.mkdir(); + this.webJobDir = new File(webDir, "jobs"); + webJobDir.mkdir(); + this.webOverviewDir = new File(webDir, "overviews"); + webOverviewDir.mkdir(); + } + + @Override + public void run() { + try { + for (HistoryServer.RefreshLocation refreshLocation : refreshDirs) { + Path refreshDir = refreshLocation.getPath(); + FileSystem refreshFS = refreshLocation.getFs(); + + // contents of /:refreshDir + FileStatus[] jobArchives; + try { + jobArchives = refreshFS.listStatus(refreshDir); + } catch (IOException e) { + LOG.error("Failed to access job archive location for path {}.", refreshDir, e); + continue; + } + if (jobArchives == null) { + continue; + } + boolean updateOverview = false; + for (FileStatus jobArchive : jobArchives) { + Path jobArchivePath = jobArchive.getPath(); + String jobID = jobArchivePath.getName(); + try { + JobID.fromHexString(jobID); + } catch (IllegalArgumentException iae) { + LOG.debug("Archive directory {} contained file with unexpected name {}. Ignoring file.", + refreshDir, jobID, iae); + continue; + } + if (cachedArchives.put(jobID, refreshDir) == null) { --- End diff -- I think we need to take the modifcation time into account here as well :-( For HA, the same job is potentially suspended and archived multiple times. We will currently only display the first HA run.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---