t;, e);
}
SecretKey shuffleKey = keyGen.generateKey();
TokenCache.setShuffleSecretKey(shuffleKey.getEncoded(),
job.getCredentials());
}
if (CryptoUtils.isEncryptedSpillEnabled(conf)) {
conf.setInt(MRJobConfig.MR_AM_MAX_ATTEMPTS, 1);
LOG.warn("Max job attempts set to 1 since encrypted intermediate" +
"data spill is enabled");
}
// 拷贝jar包到集群
// 此方法中调用如下方法:rUploader.uploadFiles(job, jobSubmitDir);
// uploadFiles方法将jar包拷贝到集群
copyAndConfigureFiles(job, submitJobDir);
Path submitJobFile = JobSubmissionFiles.getJobConfPath(submitJobDir);
// Create the splits for the job
LOG.debug("Creating splits at " + jtFs.makeQualified(submitJobDir));
// 计算切片,生成切片规划文件
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);
if (conf.getBoolean(
MRJobConfig.JOB_TOKEN_TRACKING_IDS_ENABLED,
MRJobConfig.DEFAULT_JOB_TOKEN_TRACKING_IDS_ENABLED)) {
// Add HDFS tracking ids
ArrayList<String> trackingIds = new ArrayList<String>();
for (Token<? extends TokenIdentifier> t :
job.getCredentials().getAllTokens()) {
trackingIds.add(t.decodeIdentifier().getTrackingId());
}
conf.setStrings(MRJobConfig.JOB_TOKEN_TRACKING_IDS,
trackingIds.toArray(new String[trackingIds.size()]));
}
// Set reservation info if it exists
ReservationId reservationId = job.getReservationId();
if (reservationId != null) {
conf.set(MRJobConfig.RESERVATION_ID, reservationId.toString());
}
// Write job file to submit dir
writeConf(conf, submitJobFile);
//
// Now, actually submit the job (using the submit name)
// 开始正式提交job
printTokens(jobId, job.getCredentials());
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);
}
}
}
- 进入
writeSplits(job, submitJobDir) ,计算切片,生成切片规划文件
- 内部会调用
writeNewSplits(job, jobSubmitDir) 方法
writeNewSplits(job, jobSubmitDir) 内部定义了一个InputFormat 类型的实例input
- InputFormat主要作用:
- 验证job的输入规范
- 对输入的文件进行切分,形成多个InputSplit(切片)文件,每一个InputSplit对应着一个map任务(MapTask)
- 将切片后的数据按照规则形成key,value键值对RecordReader
- input调用getSplits()方法:
List<InputSplit> splits = input.getSplits(job);
- 进入FileInputFormat类下的
getSplits(job) 方法
/**
* Generate the list of files and make them into FileSplits.
* @param job the job context
* @throws IOException
*/
public List<InputSplit> getSplits(JobContext job) throws IOException {
S
|