From 8f0d3d69d65a252439610e6f13d679808d768569 Mon Sep 17 00:00:00 2001 From: Sangjin Lee Date: Tue, 19 Jul 2016 20:15:37 -0700 Subject: [PATCH] MAPREDUCE-6365. Refactor JobResourceUploader#uploadFilesInternal (Chris Trezzo via sjlee) --- .../hadoop/mapreduce/JobResourceUploader.java | 62 ++++++++++++------- .../apache/hadoop/mapreduce/JobSubmitter.java | 2 +- 2 files changed, 40 insertions(+), 24 deletions(-) diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobResourceUploader.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobResourceUploader.java index 90e1fba765..fa4dd86f3d 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobResourceUploader.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobResourceUploader.java @@ -54,7 +54,7 @@ class JobResourceUploader { * @param submitJobDir the submission directory of the job * @throws IOException */ - public void uploadFiles(Job job, Path submitJobDir) throws IOException { + public void uploadResources(Job job, Path submitJobDir) throws IOException { Configuration conf = job.getConfiguration(); short replication = (short) conf.getInt(Job.SUBMIT_REPLICATION, @@ -66,12 +66,6 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { + "with ToolRunner to remedy this."); } - // get all the command line arguments passed in by the user conf - String files = conf.get("tmpfiles"); - String libjars = conf.get("tmpjars"); - String archives = conf.get("tmparchives"); - String jobJar = job.getJar(); - // // Figure out what fs the JobTracker is using. Copy the // job to it, under a temporary name. This allows DFS to work, @@ -92,12 +86,27 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { FsPermission mapredSysPerms = new FsPermission(JobSubmissionFiles.JOB_DIR_PERMISSION); FileSystem.mkdirs(jtFs, submitJobDir, mapredSysPerms); - Path filesDir = JobSubmissionFiles.getJobDistCacheFiles(submitJobDir); - Path archivesDir = JobSubmissionFiles.getJobDistCacheArchives(submitJobDir); - Path libjarsDir = JobSubmissionFiles.getJobDistCacheLibjars(submitJobDir); // add all the command line files/ jars and archive // first copy them to jobtrackers filesystem + uploadFiles(conf, submitJobDir, mapredSysPerms, replication); + uploadLibJars(conf, submitJobDir, mapredSysPerms, replication); + uploadArchives(conf, submitJobDir, mapredSysPerms, replication); + uploadJobJar(job, submitJobDir, replication); + addLog4jToDistributedCache(job, submitJobDir); + + // set the timestamps of the archives and files + // set the public/private visibility of the archives and files + ClientDistributedCacheManager.determineTimestampsAndCacheVisibilities(conf); + // get DelegationToken for cached file + ClientDistributedCacheManager.getDelegationTokens(conf, + job.getCredentials()); + } + + private void uploadFiles(Configuration conf, Path submitJobDir, + FsPermission mapredSysPerms, short submitReplication) throws IOException { + String files = conf.get("tmpfiles"); + Path filesDir = JobSubmissionFiles.getJobDistCacheFiles(submitJobDir); if (files != null) { FileSystem.mkdirs(jtFs, filesDir, mapredSysPerms); String[] fileArr = files.split(","); @@ -109,7 +118,7 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { throw new IllegalArgumentException(e); } Path tmp = new Path(tmpURI); - Path newPath = copyRemoteFiles(filesDir, tmp, conf, replication); + Path newPath = copyRemoteFiles(filesDir, tmp, conf, submitReplication); try { URI pathURI = getPathURI(newPath, tmpURI.getFragment()); DistributedCache.addCacheFile(pathURI, conf); @@ -119,13 +128,19 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { } } } + } + private void uploadLibJars(Configuration conf, Path submitJobDir, + FsPermission mapredSysPerms, short submitReplication) throws IOException { + String libjars = conf.get("tmpjars"); + Path libjarsDir = JobSubmissionFiles.getJobDistCacheLibjars(submitJobDir); if (libjars != null) { FileSystem.mkdirs(jtFs, libjarsDir, mapredSysPerms); String[] libjarsArr = libjars.split(","); for (String tmpjars : libjarsArr) { Path tmp = new Path(tmpjars); - Path newPath = copyRemoteFiles(libjarsDir, tmp, conf, replication); + Path newPath = + copyRemoteFiles(libjarsDir, tmp, conf, submitReplication); // Add each file to the classpath DistributedCache.addFileToClassPath( @@ -140,7 +155,12 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { DistributedCache.addCacheFile(libJarsDirWildcard.toUri(), conf); } } + } + private void uploadArchives(Configuration conf, Path submitJobDir, + FsPermission mapredSysPerms, short submitReplication) throws IOException { + String archives = conf.get("tmparchives"); + Path archivesDir = JobSubmissionFiles.getJobDistCacheArchives(submitJobDir); if (archives != null) { FileSystem.mkdirs(jtFs, archivesDir, mapredSysPerms); String[] archivesArr = archives.split(","); @@ -152,7 +172,8 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { throw new IllegalArgumentException(e); } Path tmp = new Path(tmpURI); - Path newPath = copyRemoteFiles(archivesDir, tmp, conf, replication); + Path newPath = + copyRemoteFiles(archivesDir, tmp, conf, submitReplication); try { URI pathURI = getPathURI(newPath, tmpURI.getFragment()); DistributedCache.addCacheArchive(pathURI, conf); @@ -162,7 +183,11 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { } } } + } + private void uploadJobJar(Job job, Path submitJobDir, short submitReplication) + throws IOException { + String jobJar = job.getJar(); if (jobJar != null) { // copy jar to JobTracker's fs // use jar name if job is not named. if ("".equals(job.getJobName())) { @@ -174,22 +199,13 @@ public void uploadFiles(Job job, Path submitJobDir) throws IOException { // we don't need to copy it from local fs if (jobJarURI.getScheme() == null || jobJarURI.getScheme().equals("file")) { copyJar(jobJarPath, JobSubmissionFiles.getJobJar(submitJobDir), - replication); + submitReplication); job.setJar(JobSubmissionFiles.getJobJar(submitJobDir).toString()); } } else { LOG.warn("No job jar file set. User classes may not be found. " + "See Job or Job#setJar(String)."); } - - addLog4jToDistributedCache(job, submitJobDir); - - // set the timestamps of the archives and files - // set the public/private visibility of the archives and files - ClientDistributedCacheManager.determineTimestampsAndCacheVisibilities(conf); - // get DelegationToken for cached file - ClientDistributedCacheManager.getDelegationTokens(conf, - job.getCredentials()); } // copies a file to the jobtracker filesystem and returns the path where it diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmitter.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmitter.java index 22874e10fd..d1cc72c566 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmitter.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmitter.java @@ -99,7 +99,7 @@ private void copyAndConfigureFiles(Job job, Path jobSubmitDir) Job.DEFAULT_USE_WILDCARD_FOR_LIBJARS); JobResourceUploader rUploader = new JobResourceUploader(jtFs, useWildcards); - rUploader.uploadFiles(job, jobSubmitDir); + rUploader.uploadResources(job, jobSubmitDir); // Get the working directory. If not set, sets it to filesystem working dir // This code has been added so that working directory reset before running