/**
* Sets the connector information needed to communicate with Accumulo in this job.
*
* <p><b>WARNING:</b> Some tokens, when serialized, divulge sensitive information in the
* configuration as a means to pass the token to MapReduce tasks. This information is BASE64
* encoded to provide a charset safe conversion to a string, but this conversion is not intended
* to be secure. {@link PasswordToken} is one example that is insecure in this way; however {@link
* DelegationToken}s, acquired using {@link
* SecurityOperations#getDelegationToken(DelegationTokenConfig)}, is not subject to this concern.
*
* @param job the Hadoop job instance to be configured
* @param principal a valid Accumulo user name (user must have Table.CREATE permission)
* @param token the user's password
* @since 1.5.0
*/
public static void setConnectorInfo(Job job, String principal, AuthenticationToken token)
throws AccumuloSecurityException {
if (token instanceof KerberosToken) {
log.info("Received KerberosToken, attempting to fetch DelegationToken");
try {
Instance instance = getInstance(job);
Connector conn = instance.getConnector(principal, token);
token = conn.securityOperations().getDelegationToken(new DelegationTokenConfig());
} catch (Exception e) {
log.warn(
"Failed to automatically obtain DelegationToken, Mappers/Reducers will likely fail to communicate with Accumulo",
e);
}
}
// DelegationTokens can be passed securely from user to task without serializing insecurely in
// the configuration
if (token instanceof DelegationTokenImpl) {
DelegationTokenImpl delegationToken = (DelegationTokenImpl) token;
// Convert it into a Hadoop Token
AuthenticationTokenIdentifier identifier = delegationToken.getIdentifier();
Token<AuthenticationTokenIdentifier> hadoopToken =
new Token<>(
identifier.getBytes(),
delegationToken.getPassword(),
identifier.getKind(),
delegationToken.getServiceName());
// Add the Hadoop Token to the Job so it gets serialized and passed along.
job.getCredentials().addToken(hadoopToken.getService(), hadoopToken);
}
InputConfigurator.setConnectorInfo(CLASS, job.getConfiguration(), principal, token);
}
/**
* Create input listing by invoking an appropriate copy listing implementation. Also add
* delegation tokens for each path to job's credential store
*
* @param job - Handle to job
* @return Returns the path where the copy listing is created
* @throws IOException - If any
*/
protected Path createInputFileListing(Job job) throws IOException {
Path fileListingPath = getFileListingPath();
CopyListing copyListing =
CopyListing.getCopyListing(job.getConfiguration(), job.getCredentials(), inputOptions);
copyListing.buildListing(fileListingPath, inputOptions);
LOG.info("Number of paths considered for copy: " + copyListing.getNumberOfPaths());
LOG.info(
"Number of bytes considered for copy: "
+ copyListing.getBytesToCopy()
+ " (Actual number of bytes copied depends on whether any files are "
+ "skipped or overwritten.)");
return fileListingPath;
}
private void populateTokens(Job job) {
// Credentials in the job will not have delegation tokens
// because security is disabled. Fetch delegation tokens
// and populate the credential in the job.
try {
Credentials ts = job.getCredentials();
Path p1 = new Path("file1");
p1 = p1.getFileSystem(job.getConfiguration()).makeQualified(p1);
Credentials cred = new Credentials();
TokenCache.obtainTokensForNamenodesInternal(cred, new Path[] {p1}, job.getConfiguration());
for (Token<? extends TokenIdentifier> t : cred.getAllTokens()) {
ts.addToken(new Text("Hdfs"), t);
}
} catch (IOException e) {
Assert.fail("Exception " + e);
}
}
/**
* Internal method for submitting jobs to the system.
*
* <p>The job submission process involves:
*
* <ol>
* <li>Checking the input and output specifications of the job.
* <li>Computing the {@link InputSplit}s for the job.
* <li>Setup the requisite accounting information for the {@link DistributedCache} of the job,
* if necessary.
* <li>Copying the job's jar and configuration to the map-reduce system directory on the
* distributed file-system.
* <li>Submitting the job to the <code>JobTracker</code> and optionally monitoring it's status.
* </ol>
*
* @param job the configuration to submit
* @param cluster the handle to the Cluster
* @throws ClassNotFoundException
* @throws InterruptedException
* @throws IOException
*/
JobStatus submitJobInternal(Job job, Cluster cluster)
throws ClassNotFoundException, InterruptedException, IOException {
// validate the jobs output specs
//// check use new api or not. check output valid or invalid.
checkSpecs(job);
//// usually, /tmp/username as staging area.
Path jobStagingArea = JobSubmissionFiles.getStagingDir(cluster, job.getConfiguration());
// configure the command line options correctly on the submitting dfs
Configuration conf = job.getConfiguration();
InetAddress ip = InetAddress.getLocalHost();
if (ip != null) {
submitHostAddress = ip.getHostAddress();
submitHostName = ip.getHostName();
conf.set(MRJobConfig.JOB_SUBMITHOST, submitHostName);
conf.set(MRJobConfig.JOB_SUBMITHOSTADDR, submitHostAddress);
}
JobID jobId = submitClient.getNewJobID();
job.setJobID(jobId);
Path submitJobDir = new Path(jobStagingArea, jobId.toString());
JobStatus status = null;
try {
conf.set(
"hadoop.http.filter.initializers",
"org.apache.hadoop.yarn.server.webproxy.amfilter.AmFilterInitializer");
//// set mapreduce_job_dir as job staging tmp dir.
conf.set(MRJobConfig.MAPREDUCE_JOB_DIR, submitJobDir.toString());
LOG.debug("Configuring job " + jobId + " with " + submitJobDir + " as the submit dir");
// get delegation token for the dir
// secret be stored in TokenCache before job be submitted. and get secret during job running.
//// this is a static method.
//// secret stored before submission and read during task.
TokenCache.obtainTokensForNamenodes(job.getCredentials(), new Path[] {submitJobDir}, conf);
//// get secret keys and store them into TokenCache.
populateTokenCache(conf, job.getCredentials());
//// copy lib、files... into submitJobDir
copyAndConfigureFiles(job, submitJobDir);
//// change job.xml dir to Path.
Path submitJobFile = JobSubmissionFiles.getJobConfPath(submitJobDir);
// Create the splits for the job
LOG.debug("Creating splits at " + jtFs.makeQualified(submitJobDir));
//// InputFormat.getSplits()
int maps = writeSplits(job, submitJobDir);
conf.setInt(MRJobConfig.NUM_MAPS, maps);
LOG.info("number of splits:" + maps);
// write "queue admins of the queue to which job is being submitted"
// to job file.
String queue = conf.get(MRJobConfig.QUEUE_NAME, JobConf.DEFAULT_QUEUE_NAME);
AccessControlList acl = submitClient.getQueueAdmins(queue);
conf.set(
toFullPropertyName(queue, QueueACL.ADMINISTER_JOBS.getAclName()), acl.getAclString());
// removing jobtoken referrals before copying the jobconf to HDFS
// as the tasks don't need this setting, actually they may break
// because of it if present as the referral will point to a
// different job.
TokenCache.cleanUpTokenReferral(conf);
// Write job file to submit dir
writeConf(conf, submitJobFile);
//
// Now, actually submit the job (using the submit name)
//
printTokens(jobId, job.getCredentials());
//// find implement usage of submitJob, result: YARNRunner and LocalJobRunner
status = submitClient.submitJob(jobId, submitJobDir.toString(), job.getCredentials());
if (status != null) {
return status;
} else {
throw new IOException("Could not launch job");
}
} finally {
if (status == null) {
LOG.info("Cleaning up the staging area " + submitJobDir);
if (jtFs != null && submitJobDir != null) jtFs.delete(submitJobDir, true);
}
}
}
// configures -files, -libjars and -archives.
//// default replication is 10
private void copyAndConfigureFiles(Job job, Path submitJobDir, short replication)
throws IOException {
Configuration conf = job.getConfiguration();
if (!(conf.getBoolean(Job.USED_GENERIC_PARSER, false))) {
LOG.warn(
"Use GenericOptionsParser for parsing the arguments. "
+ "Applications should implement Tool for the same.");
}
// 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");
//// "mapreduce.job.jar"
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,
// 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
LOG.debug("default FileSystem: " + jtFs.getUri());
if (jtFs.exists(submitJobDir)) {
throw new IOException(
"Not submitting job. Job directory "
+ submitJobDir
+ " already exists!! This is unexpected.Please check what's there in"
+ " that directory");
}
submitJobDir = jtFs.makeQualified(submitJobDir);
submitJobDir = new Path(submitJobDir.toUri().getPath());
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
if (files != null) {
FileSystem.mkdirs(jtFs, filesDir, mapredSysPerms);
String[] fileArr = files.split(",");
for (String tmpFile : fileArr) {
URI tmpURI = null;
try {
tmpURI = new URI(tmpFile);
} catch (URISyntaxException e) {
throw new IllegalArgumentException(e);
}
Path tmp = new Path(tmpURI);
Path newPath = copyRemoteFiles(filesDir, tmp, conf, replication);
try {
URI pathURI = getPathURI(newPath, tmpURI.getFragment());
DistributedCache.addCacheFile(pathURI, conf);
} catch (URISyntaxException ue) {
// should not throw a uri exception
throw new IOException("Failed to create uri for " + tmpFile, ue);
}
DistributedCache.createSymlink(conf);
}
}
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);
DistributedCache.addFileToClassPath(new Path(newPath.toUri().getPath()), conf);
}
}
if (archives != null) {
FileSystem.mkdirs(jtFs, archivesDir, mapredSysPerms);
String[] archivesArr = archives.split(",");
for (String tmpArchives : archivesArr) {
URI tmpURI;
try {
tmpURI = new URI(tmpArchives);
} catch (URISyntaxException e) {
throw new IllegalArgumentException(e);
}
Path tmp = new Path(tmpURI);
Path newPath = copyRemoteFiles(archivesDir, tmp, conf, replication);
try {
URI pathURI = getPathURI(newPath, tmpURI.getFragment());
DistributedCache.addCacheArchive(pathURI, conf);
} catch (URISyntaxException ue) {
// should not throw an uri excpetion
throw new IOException("Failed to create uri for " + tmpArchives, ue);
}
DistributedCache.createSymlink(conf);
}
}
if (jobJar != null) { // copy jar to JobTracker's fs
// use jar name if job is not named.
if ("".equals(job.getJobName())) {
job.setJobName(new Path(jobJar).getName());
}
copyJar(new Path(jobJar), JobSubmissionFiles.getJobJar(submitJobDir), replication);
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).");
}
// set the timestamps of the archives and files
ClientDistributedCacheManager.determineTimestamps(conf);
// set the public/private visibility of the archives and files
ClientDistributedCacheManager.determineCacheVisibilities(conf);
// get DelegationToken for each cached file
ClientDistributedCacheManager.getDelegationTokens(conf, job.getCredentials());
}