/*
* set this user's id in job configuration, so later job files can be
* accessed using this user's id
*/
UnixUserGroupInformation ugi = getUGI(job);
//
// Figure out what fs the JobTracker is using. Copy the
// job to it, under a temporary name. This allows DFS to work,
// and under the local fs also provides UNIX-like object loading
// semantics. (that is, if the job file is deleted right after
// submission, we can still run the submission to completion)
//
// Create a number of filenames in the JobTracker's fs namespace
FileSystem fs = getFs();
LOG.debug("default FileSystem: " + fs.getUri());
fs.delete(submitJobDir, true);
submitJobDir = fs.makeQualified(submitJobDir);
submitJobDir = new Path(submitJobDir.toUri().getPath());
FsPermission mapredSysPerms = new FsPermission(JOB_DIR_PERMISSION);
FileSystem.mkdirs(fs, submitJobDir, mapredSysPerms);
Path filesDir = new Path(submitJobDir, "files");
Path archivesDir = new Path(submitJobDir, "archives");
Path libjarsDir = new Path(submitJobDir, "libjars");
short replication = (short)job.getInt("mapred.submit.replication", 10);
// add all the command line files/ jars and archive
// first copy them to jobtrackers filesystem
if (files != null) {
FileSystem.mkdirs(fs, filesDir, mapredSysPerms);
String[] fileArr = files.split(",");
for (String tmpFile: fileArr) {
Path tmp = new Path(tmpFile);
Path newPath = copyRemoteFiles(fs,filesDir, tmp, job, replication);
try {
URI pathURI = new URI(newPath.toUri().toString() + "#" + newPath.getName());
DistributedCache.addCacheFile(pathURI, job);
} catch(URISyntaxException ue) {
//should not throw a uri exception
throw new IOException("Failed to create uri for " + tmpFile);
}
DistributedCache.createSymlink(job);
}
}
if (libjars != null) {
FileSystem.mkdirs(fs, libjarsDir, mapredSysPerms);
String[] libjarsArr = libjars.split(",");
for (String tmpjars: libjarsArr) {
Path tmp = new Path(tmpjars);
Path newPath = copyRemoteFiles(fs, libjarsDir, tmp, job, replication);
DistributedCache.addArchiveToClassPath(newPath, job);
}
}
if (archives != null) {
FileSystem.mkdirs(fs, archivesDir, mapredSysPerms);
String[] archivesArr = archives.split(",");
for (String tmpArchives: archivesArr) {
Path tmp = new Path(tmpArchives);
Path newPath = copyRemoteFiles(fs, archivesDir, tmp, job, replication);
try {
URI pathURI = new URI(newPath.toUri().toString() + "#" + newPath.getName());
DistributedCache.addCacheArchive(pathURI, job);
} catch(URISyntaxException ue) {
//should not throw an uri excpetion
throw new IOException("Failed to create uri for " + tmpArchives);
}
DistributedCache.createSymlink(job);
}
}
// set the timestamps of the archives and files
URI[] tarchives = DistributedCache.getCacheArchives(job);
if (tarchives != null) {
StringBuffer archiveTimestamps =
new StringBuffer(String.valueOf(DistributedCache.getTimestamp(job, tarchives[0])));
for (int i = 1; i < tarchives.length; i++) {
archiveTimestamps.append(",");
archiveTimestamps.append(String.valueOf(DistributedCache.getTimestamp(job, tarchives[i])));
}
DistributedCache.setArchiveTimestamps(job, archiveTimestamps.toString());
}
URI[] tfiles = DistributedCache.getCacheFiles(job);
if (tfiles != null) {
StringBuffer fileTimestamps =
new StringBuffer(String.valueOf(DistributedCache.getTimestamp(job, tfiles[0])));
for (int i = 1; i < tfiles.length; i++) {
fileTimestamps.append(",");
fileTimestamps.append(String.valueOf(DistributedCache.getTimestamp(job, tfiles[i])));
}
DistributedCache.setFileTimestamps(job, fileTimestamps.toString());
}
String originalJarPath = job.getJar();
if (originalJarPath != null) { // copy jar to JobTracker's fs
// use jar name if job is not named.
if ("".equals(job.getJobName())){
job.setJobName(new Path(originalJarPath).getName());
}
job.setJar(submitJarFile.toString());
fs.copyFromLocalFile(new Path(originalJarPath), submitJarFile);
fs.setReplication(submitJarFile, replication);
fs.setPermission(submitJarFile, new FsPermission(JOB_FILE_PERMISSION));
} else {
LOG.warn("No job jar file set. User classes may not be found. "+
"See JobConf(Class) or JobConf#setJar(String).");
}
// Set the user's name and working directory
job.setUser(ugi.getUserName());
if (ugi.getGroupNames().length > 0) {
job.set("group.name", ugi.getGroupNames()[0]);
}
if (job.getWorkingDirectory() == null) {
job.setWorkingDirectory(fs.getWorkingDirectory());
}