本文是基于hadoop2.6.5的源碼分析。
用戶端源碼分析
啟動的用戶端代碼
public static void main(String[] args) throws Exception {
// 建立配置檔案對象
Configuration conf = new Configuration(true);
// 擷取Job對象
Job job = Job.getInstance(conf);
// 設定相關類
job.setJarByClass(WcTest.class);
// 指定 Map階段和Reduce階段的處理類
job.setMapperClass(MyMapperTask.class);
job.setReducerClass(MyReducerTask.class);
// 指定Map階段的輸出類型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// 指定job的原始檔案的輸入輸出路徑 通過參數傳入
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 送出任務，并等待響應
job.waitForCompletion(true);
} 1.Configuration 對象
Configuration 用來存儲相關的配置檔案。在該類中有一段static代碼塊
2.Job對象的擷取
我們來看下Job對象的執行個體化過程。
// 擷取Job對象
Job job = Job.getInstance(conf); 進入getInstance(conf)方法。
public static Job getInstance(Configuration conf) throws IOException {
// create with a null Cluster
JobConf jobConf = new JobConf(conf);
return new Job(jobConf);
} Job類中同樣有static代碼塊。
進入loadResources方法
3.waitForCompletion
該方法的執行過程比較複雜，我們慢慢來分析，首先來看下簡化的時序圖
3.1waitForCompletion
public boolean waitForCompletion(boolean verbose
) throws IOException, InterruptedException,
ClassNotFoundException {
// 判斷任務的狀态，如果是DEFINE就送出
if (state == JobState.DEFINE) {
submit();
}
if (verbose) {
// 監聽并且輸出任務資訊
monitorAndPrintJob();
} else {
// get the completion poll interval from the client.
int completionPollIntervalMillis =
Job.getCompletionPollInterval(cluster.getConf());
while (!isComplete()) {
try {
// 間隔判斷是否執行完成
Thread.sleep(completionPollIntervalMillis);
} catch (InterruptedException ie) {
}
}
}
return isSuccessful();
} 3.2submit
進入submit方法檢視
public void submit()
throws IOException, InterruptedException, ClassNotFoundException {
// 再次确認任務狀态
ensureState(JobState.DEFINE);
// 預設使用new APIs
setUseNewAPI();
// 初始化cluster對象
connect();
// 根據初始化得到的cluster對象生成JobSubmitter對象
final JobSubmitter submitter =
getJobSubmitter(cluster.getFileSystem(), cluster.getClient());
//
status = ugi.doAs(new PrivilegedExceptionAction<JobStatus>() {
public JobStatus run() throws IOException, InterruptedException,
ClassNotFoundException {
// 進入 submitJobInternal 方法檢視
return submitter.submitJobInternal(Job.this, cluster);
}
});
//将job的狀态設定為RUNNING
state = JobState.RUNNING;
LOG.info("The url to track the job: " + getTrackingURL());
} 3.3 submitJobInternal
/**
*
* 檢查job的輸入輸出規範
* 計算job的InputSplit
* 如果需要的話，設定需要的核算資訊對于job的分布式緩存
* 複制job的jar和配置檔案到分布式檔案系統的系統目錄
* 送出作業執行以及監控它的狀态
*/
JobStatus submitJobInternal(Job job, Cluster cluster)
throws ClassNotFoundException, InterruptedException, IOException {
//檢查job的輸出空間
checkSpecs(job);
Configuration conf = job.getConfiguration();
// 将MapReduce架構加入分布式緩存中
addMRFrameworkToDistributedCache(conf);
// 初始化job的工作根目錄并傳回path路徑
Path jobStagingArea = JobSubmissionFiles.getStagingDir(cluster, conf);
//configure the command line options correctly on the submitting dfs
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);
}
// 為job配置設定一個名字
JobID jobId = submitClient.getNewJobID();
job.setJobID(jobId);
// 獲得job的送出路徑，也就是在jobStagingArea目錄下建一個以jobId為檔案名的目錄
Path submitJobDir = new Path(jobStagingArea, jobId.toString());
JobStatus status = null;
// 進行一系列的配置
try {
conf.set(MRJobConfig.USER_NAME,
UserGroupInformation.getCurrentUser().getShortUserName());
conf.set("hadoop.http.filter.initializers",
"org.apache.hadoop.yarn.server.webproxy.amfilter.AmFilterInitializer");
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
TokenCache.obtainTokensForNamenodes(job.getCredentials(),
new Path[] { submitJobDir }, conf);
populateTokenCache(conf, job.getCredentials());
// generate a secret to authenticate shuffle transfers
if (TokenCache.getShuffleSecretKey(job.getCredentials()) == null) {
KeyGenerator keyGen;
try {
keyGen = KeyGenerator.getInstance(SHUFFLE_KEYGEN_ALGORITHM);
keyGen.init(SHUFFLE_KEY_LENGTH);
} catch (NoSuchAlgorithmException e) {
throw new IOException("Error generating shuffle secret key", e);
}
SecretKey shuffleKey = keyGen.generateKey();
TokenCache.setShuffleSecretKey(shuffleKey.getEncoded(),
job.getCredentials());
}
// 這個方法實作檔案上傳
copyAndConfigureFiles(job, submitJobDir);
Path submitJobFile = JobSubmissionFiles.getJobConfPath(submitJobDir);
// Create the splits for the job
LOG.debug("Creating splits at " + jtFs.makeQualified(submitJobDir));
// 方法内部會根據我們之前的設定，選擇使用new-api還是old-api分别進行分片操作
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()]));
}
// 送出規劃檔案 job.split wc.jar ...
writeConf(conf, submitJobFile);
//
// Now, actually submit the job (using the submit name)
// 送出任務
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);
}
}
} 3.4writeSplits
private int writeSplits(org.apache.hadoop.mapreduce.JobContext job,
Path jobSubmitDir) throws IOException,
InterruptedException, ClassNotFoundException {
JobConf jConf = (JobConf)job.getConfiguration();
int maps;
if (jConf.getUseNewMapper()) {
//進入
maps = writeNewSplits(job, jobSubmitDir);
} else {
maps = writeOldSplits(jConf, jobSubmitDir);
}
return maps;
} 3.5writeNewSplits
int writeNewSplits(JobContext job, Path jobSubmitDir) throws IOException,
InterruptedException, ClassNotFoundException {
Configuration conf = job.getConfiguration();
// 根據我們設定的inputFormat.class通過反射獲得inputFormat對象
InputFormat<?, ?> input =
ReflectionUtils.newInstance(job.getInputFormatClass(), conf);
// 擷取分片資訊
List<InputSplit> splits = input.getSplits(job);
T[] array = (T[]) splits.toArray(new InputSplit[splits.size()]);
// sort the splits into order based on size, so that the biggest
// go first
Arrays.sort(array, new SplitComparator());
// 将分片的資訊寫入到jobSubmitDir --job.split檔案中
JobSplitWriter.createSplitFiles(jobSubmitDir, conf,
jobSubmitDir.getFileSystem(conf), array);
return array.length;
} 3.6 getSplits
public List<InputSplit> getSplits(JobContext job) throws IOException {
Stopwatch sw = new Stopwatch().start();
// 最小值
long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
// 最大值
long maxSize = getMaxSplitSize(job);
// generate splits
List<InputSplit> splits = new ArrayList<InputSplit>();
List<FileStatus> files = listStatus(job);
for (FileStatus file: files) {
Path path = file.getPath();
long length = file.getLen();
if (length != 0) {
BlockLocation[] blkLocations;
if (file instanceof LocatedFileStatus) {
blkLocations = ((LocatedFileStatus) file).getBlockLocations();
} else {
FileSystem fs = path.getFileSystem(job.getConfiguration());
blkLocations = fs.getFileBlockLocations(file, 0, length);
}
if (isSplitable(job, path)) {
// 擷取block大小
long blockSize = file.getBlockSize();
// 擷取splitSize大小
long splitSize = computeSplitSize(blockSize, minSize, maxSize);
long bytesRemaining = length;
while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(makeSplit(path, length-bytesRemaining, splitSize,
blkLocations[blkIndex].getHosts(),
blkLocations[blkIndex].getCachedHosts()));
bytesRemaining -= splitSize;
}
if (bytesRemaining != 0) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(makeSplit(path, length-bytesRemaining, bytesRemaining,
blkLocations[blkIndex].getHosts(),
blkLocations[blkIndex].getCachedHosts()));
}
} else { // not splitable
splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts(),
blkLocations[0].getCachedHosts()));
}
} else {
//Create empty hosts array for zero length files
splits.add(makeSplit(path, 0, length, new String[0]));
}
}
// Save the number of input files for metrics/loadgen
job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
sw.stop();
if (LOG.isDebugEnabled()) {
LOG.debug("Total # of splits generated by getSplits: " + splits.size()
+ ", TimeTaken: " + sw.elapsedMillis());
}
return splits;
} 3.7computeSplitSize
protected long computeSplitSize(long blockSize, long minSize,
long maxSize) {
return Math.max(minSize, Math.min(maxSize, blockSize));
} 3.8 submitJobInternal
回到 submitJobInternal方法中
// 送出規劃檔案 job.split wc.jar ...
writeConf(conf, submitJobFile);
//
// Now, actually submit the job (using the submit name)
// 送出任務
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)
// 删除規劃檔案
jtFs.delete(submitJobDir, true);
}
} 至此整理流程代碼看完~ 詳細的可以多看下源碼