一.简介
创建Application是由client向ResourceManager发起申请，client与RM之间的通信依靠Hadoop RPC，通信协议是ApplicationClientProtocol，所谓通信协议实际上就是一个接口，接口中说明了server/client具备哪些操作函数。
二.源码
2.1 Client
代码语言：javascript复制public boolean run() throws IOException, YarnException {
LOG.info("Running Client");
yarnClient.start();
YarnClusterMetrics clusterMetrics = yarnClient.getYarnClusterMetrics();
LOG.info("Got Cluster metric info from ASM"
", numNodeManagers=" clusterMetrics.getNumNodeManagers());
List<NodeReport> clusterNodeReports = yarnClient.getNodeReports(
NodeState.RUNNING);
LOG.info("Got Cluster node info from ASM");
for (NodeReport node : clusterNodeReports) {
LOG.info("Got node report from ASM for"
", nodeId=" node.getNodeId()
", nodeAddress" node.getHttpAddress()
", nodeRackName" node.getRackName()
", nodeNumContainers" node.getNumContainers());
}
QueueInfo queueInfo = yarnClient.getQueueInfo(this.amQueue);
LOG.info("Queue info"
", queueName=" queueInfo.getQueueName()
", queueCurrentCapacity=" queueInfo.getCurrentCapacity()
", queueMaxCapacity=" queueInfo.getMaximumCapacity()
", queueApplicationCount=" queueInfo.getApplications().size()
", queueChildQueueCount=" queueInfo.getChildQueues().size());
List<QueueUserACLInfo> listAclInfo = yarnClient.getQueueAclsInfo();
for (QueueUserACLInfo aclInfo : listAclInfo) {
for (QueueACL userAcl : aclInfo.getUserAcls()) {
LOG.info("User ACL Info for Queue"
", queueName=" aclInfo.getQueueName()
", userAcl=" userAcl.name());
}
}
if (domainId != null && domainId.length() > 0 && toCreateDomain) {
prepareTimelineDomain();
}
// Get a new application id
// 创建application
YarnClientApplication app = yarnClient.createApplication();
GetNewApplicationResponse appResponse = app.getNewApplicationResponse();
// TODO get min/max resource capabilities from RM and change memory ask if needed
// If we do not have min/max, we may not be able to correctly request
// the required resources from the RM for the app master
// Memory ask has to be a multiple of min and less than max.
// Dump out information about cluster capability as seen by the resource manager
int maxMem = appResponse.getMaximumResourceCapability().getMemory();
LOG.info("Max mem capabililty of resources in this cluster " maxMem);
// A resource ask cannot exceed the max.
if (amMemory > maxMem) {
LOG.info("AM memory specified above max threshold of cluster. Using max value."
", specified=" amMemory
", max=" maxMem);
amMemory = maxMem;
}
int maxVCores = appResponse.getMaximumResourceCapability().getVirtualCores();
LOG.info("Max virtual cores capabililty of resources in this cluster " maxVCores);
if (amVCores > maxVCores) {
LOG.info("AM virtual cores specified above max threshold of cluster. "
"Using max value." ", specified=" amVCores
", max=" maxVCores);
amVCores = maxVCores;
}
// set the application name
ApplicationSubmissionContext appContext = app.getApplicationSubmissionContext();
ApplicationId appId = appContext.getApplicationId();
appContext.setKeepContainersAcrossApplicationAttempts(keepContainers);
appContext.setApplicationName(appName);
if (attemptFailuresValidityInterval >= 0) {
appContext
.setAttemptFailuresValidityInterval(attemptFailuresValidityInterval);
}
// set local resources for the application master
// local files or archives as needed
// In this scenario, the jar file for the application master is part of the local resources
Map<String, LocalResource> localResources = new HashMap<String, LocalResource>();
LOG.info("Copy App Master jar from local filesystem and add to local environment");
// Copy the application master jar to the filesystem
// Create a local resource to point to the destination jar path
FileSystem fs = FileSystem.get(conf);
addToLocalResources(fs, appMasterJar, appMasterJarPath, appId.toString(),
localResources, null);
// Set the log4j properties if needed
if (!log4jPropFile.isEmpty()) {
addToLocalResources(fs, log4jPropFile, log4jPath, appId.toString(),
localResources, null);
}
// The shell script has to be made available on the final container(s)
// where it will be executed.
// To do this, we need to first copy into the filesystem that is visible
// to the yarn framework.
// We do not need to set this as a local resource for the application
// master as the application master does not need it.
String hdfsShellScriptLocation = "";
long hdfsShellScriptLen = 0;
long hdfsShellScriptTimestamp = 0;
if (!shellScriptPath.isEmpty()) {
Path shellSrc = new Path(shellScriptPath);
String shellPathSuffix =
appName "/" appId.toString() "/" SCRIPT_PATH;
Path shellDst =
new Path(fs.getHomeDirectory(), shellPathSuffix);
fs.copyFromLocalFile(false, true, shellSrc, shellDst);
hdfsShellScriptLocation = shellDst.toUri().toString();
FileStatus shellFileStatus = fs.getFileStatus(shellDst);
hdfsShellScriptLen = shellFileStatus.getLen();
hdfsShellScriptTimestamp = shellFileStatus.getModificationTime();
}
if (!shellCommand.isEmpty()) {
addToLocalResources(fs, null, shellCommandPath, appId.toString(),
localResources, shellCommand);
}
if (shellArgs.length > 0) {
addToLocalResources(fs, null, shellArgsPath, appId.toString(),
localResources, StringUtils.join(shellArgs, " "));
}
// Set the necessary security tokens as needed
//amContainer.setContainerTokens(containerToken);
// Set the env variables to be setup in the env where the application master will be run
LOG.info("Set the environment for the application master");
Map<String, String> env = new HashMap<String, String>();
// put location of shell script into env
// using the env info, the application master will create the correct local resource for the
// eventual containers that will be launched to execute the shell scripts
env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTLOCATION, hdfsShellScriptLocation);
env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTTIMESTAMP, Long.toString(hdfsShellScriptTimestamp));
env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTLEN, Long.toString(hdfsShellScriptLen));
if (domainId != null && domainId.length() > 0) {
env.put(DSConstants.DISTRIBUTEDSHELLTIMELINEDOMAIN, domainId);
}
// Add AppMaster.jar location to classpath
// At some point we should not be required to add
// the hadoop specific classpaths to the env.
// It should be provided out of the box.
// For now setting all required classpaths including
// the classpath to "." for the application jar
StringBuilder classPathEnv = new StringBuilder(Environment.CLASSPATH.$$())
.append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./*");
for (String c : conf.getStrings(
YarnConfiguration.YARN_APPLICATION_CLASSPATH,
YarnConfiguration.DEFAULT_YARN_CROSS_PLATFORM_APPLICATION_CLASSPATH)) {
classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR);
classPathEnv.append(c.trim());
}
classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR).append(
"./log4j.properties");
// add the runtime classpath needed for tests to work
if (conf.getBoolean(YarnConfiguration.IS_MINI_YARN_CLUSTER, false)) {
classPathEnv.append(':');
classPathEnv.append(System.getProperty("java.class.path"));
}
env.put("CLASSPATH", classPathEnv.toString());
// Set the necessary command to execute the application master
Vector<CharSequence> vargs = new Vector<CharSequence>(30);
// Set java executable command
LOG.info("Setting up app master command");
vargs.add(Environment.JAVA_HOME.$$() "/bin/java");
// Set Xmx based on am memory size
vargs.add("-Xmx" amMemory "m");
// Set class name
vargs.add(appMasterMainClass);
// Set params for Application Master
vargs.add("--container_memory " String.valueOf(containerMemory));
vargs.add("--container_vcores " String.valueOf(containerVirtualCores));
vargs.add("--num_containers " String.valueOf(numContainers));
if (null != nodeLabelExpression) {
appContext.setNodeLabelExpression(nodeLabelExpression);
}
vargs.add("--priority " String.valueOf(shellCmdPriority));
for (Map.Entry<String, String> entry : shellEnv.entrySet()) {
vargs.add("--shell_env " entry.getKey() "=" entry.getValue());
}
if (debugFlag) {
vargs.add("--debug");
}
vargs.add("1>" ApplicationConstants.LOG_DIR_EXPANSION_VAR "/AppMaster.stdout");
vargs.add("2>" ApplicationConstants.LOG_DIR_EXPANSION_VAR "/AppMaster.stderr");
// Get final commmand
StringBuilder command = new StringBuilder();
for (CharSequence str : vargs) {
command.append(str).append(" ");
}
LOG.info("Completed setting up app master command " command.toString());
List<String> commands = new ArrayList<String>();
commands.add(command.toString());
// Set up the container launch context for the application master
ContainerLaunchContext amContainer = ContainerLaunchContext.newInstance(
localResources, env, commands, null, null, null);
// Set up resource type requirements
// For now, both memory and vcores are supported, so we set memory and
// vcores requirements
Resource capability = Resource.newInstance(amMemory, amVCores);
appContext.setResource(capability);
// Service data is a binary blob that can be passed to the application
// Not needed in this scenario
// amContainer.setServiceData(serviceData);
// Setup security tokens
if (UserGroupInformation.isSecurityEnabled()) {
// Note: Credentials class is marked as LimitedPrivate for HDFS and MapReduce
Credentials credentials = new Credentials();
String tokenRenewer = conf.get(YarnConfiguration.RM_PRINCIPAL);
if (tokenRenewer == null || tokenRenewer.length() == 0) {
throw new IOException(
"Can't get Master Kerberos principal for the RM to use as renewer");
}
// For now, only getting tokens for the default file-system.
final Token<?> tokens[] =
fs.addDelegationTokens(tokenRenewer, credentials);
if (tokens != null) {
for (Token<?> token : tokens) {
LOG.info("Got dt for " fs.getUri() "; " token);
}
}
DataOutputBuffer dob = new DataOutputBuffer();
credentials.writeTokenStorageToStream(dob);
ByteBuffer fsTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength());
amContainer.setTokens(fsTokens);
}
appContext.setAMContainerSpec(amContainer);
// Set the priority for the application master
// TODO - what is the range for priority? how to decide?
Priority pri = Priority.newInstance(amPriority);
appContext.setPriority(pri);
// Set the queue to which this application is to be submitted in the RM
appContext.setQueue(amQueue);
// Submit the application to the applications manager
// SubmitApplicationResponse submitResp = applicationsManager.submitApplication(appRequest);
// Ignore the response as either a valid response object is returned on success
// or an exception thrown to denote some form of a failure
LOG.info("Submitting application to ASM");
//
yarnClient.submitApplication(appContext);
// TODO
// Try submitting the same request again
// app submission failure?
// Monitor the application
return monitorApplication(appId);
}2.1.1 Client -> YarnClientApplication app = yarnClient.createApplication();
代码语言：javascript复制YarnClientImpl
@Override
public YarnClientApplication createApplication()
throws YarnException, IOException {
ApplicationSubmissionContext context = Records.newRecord
(ApplicationSubmissionContext.class);
GetNewApplicationResponse newApp = getNewApplication();
ApplicationId appId = newApp.getApplicationId();
context.setApplicationId(appId);
return new YarnClientApplication(newApp, context);
}
private GetNewApplicationResponse getNewApplication()
throws YarnException, IOException {
GetNewApplicationRequest request =
Records.newRecord(GetNewApplicationRequest.class);
return rmClient.getNewApplication(request);
}rmClient是一个RPC client，那么getNewApplication要去RPC server才能看到是怎么实现的, 上面也说到了server端的实现在ClientRMService中，那就去里面找呗。
代码语言：javascript复制ClientRMService
ApplicationId getNewApplicationId() {
ApplicationId applicationId = org.apache.hadoop.yarn.server.utils.BuilderUtils
.newApplicationId(recordFactory, ResourceManager.getClusterTimeStamp(),
applicationCounter.incrementAndGet());
LOG.info("Allocated new applicationId: " applicationId.getId());
return applicationId;
}
@Override
public GetNewApplicationResponse getNewApplication(
GetNewApplicationRequest request) throws YarnException {
GetNewApplicationResponse response = recordFactory
.newRecordInstance(GetNewApplicationResponse.class);
response.setApplicationId(getNewApplicationId());
// Pick up min/max resource from scheduler...
response.setMaximumResourceCapability(scheduler
.getMaximumResourceCapability());
return response;
}获取ApplicationId,查询资源上下限。
2.1.2 Client -> yarnClient.submitApplication(appContext);
代码语言：javascript复制@Override
public ApplicationId
submitApplication(ApplicationSubmissionContext appContext)
throws YarnException, IOException {
ApplicationId applicationId = appContext.getApplicationId();
if (applicationId == null) {
throw new ApplicationIdNotProvidedException(
"ApplicationId is not provided in ApplicationSubmissionContext");
}
SubmitApplicationRequest request =
Records.newRecord(SubmitApplicationRequest.class);
request.setApplicationSubmissionContext(appContext);
// Automatically add the timeline DT into the CLC
// Only when the security and the timeline service are both enabled
if (isSecurityEnabled() && timelineServiceEnabled) {
addTimelineDelegationToken(appContext.getAMContainerSpec());
}
//TODO: YARN-1763:Handle RM failovers during the submitApplication call.
rmClient.submitApplication(request);
int pollCount = 0;
long startTime = System.currentTimeMillis();
EnumSet<YarnApplicationState> waitingStates =
EnumSet.of(YarnApplicationState.NEW,
YarnApplicationState.NEW_SAVING,
YarnApplicationState.SUBMITTED);
EnumSet<YarnApplicationState> failToSubmitStates =
EnumSet.of(YarnApplicationState.FAILED,
YarnApplicationState.KILLED);
while (true) {
try {
ApplicationReport appReport = getApplicationReport(applicationId);
YarnApplicationState state = appReport.getYarnApplicationState();
if (!waitingStates.contains(state)) {
if(failToSubmitStates.contains(state)) {
throw new YarnException("Failed to submit " applicationId
" to YARN : " appReport.getDiagnostics());
}
LOG.info("Submitted application " applicationId);
break;
}
long elapsedMillis = System.currentTimeMillis() - startTime;
if (enforceAsyncAPITimeout() &&
elapsedMillis >= asyncApiPollTimeoutMillis) {
throw new YarnException("Timed out while waiting for application "
applicationId " to be submitted successfully");
}
// Notify the client through the log every 10 poll, in case the client
// is blocked here too long.
if ( pollCount % 10 == 0) {
LOG.info("Application submission is not finished, "
"submitted application " applicationId
" is still in " state);
}
try {
Thread.sleep(submitPollIntervalMillis);
} catch (InterruptedException ie) {
LOG.error("Interrupted while waiting for application "
applicationId
" to be successfully submitted.");
}
} catch (ApplicationNotFoundException ex) {
// FailOver or RM restart happens before RMStateStore saves
// ApplicationState
LOG.info("Re-submit application " applicationId "with the "
"same ApplicationSubmissionContext");
rmClient.submitApplication(request);
}
}
return applicationId;
}在执行rmClient.submitApplication之后会一直轮询获取ApplicationReport来判断submit是否成功，如果失败还会进行重新提交。
代码语言：javascript复制ClientRMService
@Override
public SubmitApplicationResponse submitApplication(
SubmitApplicationRequest request) throws YarnException {
ApplicationSubmissionContext submissionContext = request
.getApplicationSubmissionContext();
ApplicationId applicationId = submissionContext.getApplicationId();
// ApplicationSubmissionContext needs to be validated for safety - only
// those fields that are independent of the RM's configuration will be
// checked here, those that are dependent on RM configuration are validated
// in RMAppManager.
String user = null;
try {
// Safety
user = UserGroupInformation.getCurrentUser().getShortUserName();
} catch (IOException ie) {
LOG.warn("Unable to get the current user.", ie);
RMAuditLogger.logFailure(user, AuditConstants.SUBMIT_APP_REQUEST,
ie.getMessage(), "ClientRMService",
"Exception in submitting application", applicationId);
throw RPCUtil.getRemoteException(ie);
}
// Check whether app has already been put into rmContext,
// If it is, simply return the response
if (rmContext.getRMApps().get(applicationId) != null) {
LOG.info("This is an earlier submitted application: " applicationId);
return SubmitApplicationResponse.newInstance();
}
if (submissionContext.getQueue() == null) {
submissionContext.setQueue(YarnConfiguration.DEFAULT_QUEUE_NAME);
}
if (submissionContext.getApplicationName() == null) {
submissionContext.setApplicationName(
YarnConfiguration.DEFAULT_APPLICATION_NAME);
}
if (submissionContext.getApplicationType() == null) {
submissionContext
.setApplicationType(YarnConfiguration.DEFAULT_APPLICATION_TYPE);
} else {
if (submissionContext.getApplicationType().length() > YarnConfiguration.APPLICATION_TYPE_LENGTH) {
submissionContext.setApplicationType(submissionContext
.getApplicationType().substring(0,
YarnConfiguration.APPLICATION_TYPE_LENGTH));
}
}
try {
// call RMAppManager to submit application directly
rmAppManager.submitApplication(submissionContext,
System.currentTimeMillis(), user);
LOG.info("Application with id " applicationId.getId()
" submitted by user " user);
RMAuditLogger.logSuccess(user, AuditConstants.SUBMIT_APP_REQUEST,
"ClientRMService", applicationId);
} catch (YarnException e) {
LOG.info("Exception in submitting application with id "
applicationId.getId(), e);
RMAuditLogger.logFailure(user, AuditConstants.SUBMIT_APP_REQUEST,
e.getMessage(), "ClientRMService",
"Exception in submitting application", applicationId);
throw e;
}
SubmitApplicationResponse response = recordFactory
.newRecordInstance(SubmitApplicationResponse.class);
return response;
}rmAppManager.submitApplication 提交application
代码语言：javascript复制@SuppressWarnings("unchecked")
protected void submitApplication(
ApplicationSubmissionContext submissionContext, long submitTime,
String user) throws YarnException {
ApplicationId applicationId = submissionContext.getApplicationId();
RMAppImpl application =
createAndPopulateNewRMApp(submissionContext, submitTime, user, false);
ApplicationId appId = submissionContext.getApplicationId();
if (UserGroupInformation.isSecurityEnabled()) {
try {
this.rmContext.getDelegationTokenRenewer().addApplicationAsync(appId,
parseCredentials(submissionContext),
submissionContext.getCancelTokensWhenComplete(),
application.getUser());
} catch (Exception e) {
LOG.warn("Unable to parse credentials.", e);
// Sending APP_REJECTED is fine, since we assume that the
// RMApp is in NEW state and thus we haven't yet informed the
// scheduler about the existence of the application
assert application.getState() == RMAppState.NEW;
this.rmContext.getDispatcher().getEventHandler()
.handle(new RMAppEvent(applicationId,
RMAppEventType.APP_REJECTED, e.getMessage()));
throw RPCUtil.getRemoteException(e);
}
} else {
// Dispatcher is not yet started at this time, so these START events
// enqueued should be guaranteed to be first processed when dispatcher
// gets started.
this.rmContext.getDispatcher().getEventHandler()
.handle(new RMAppEvent(applicationId, RMAppEventType.START));
}
}事件模型，this.rmContext.getDispatcher().getEventHandler() .handle(new RMAppEvent(applicationId, RMAppEventType.START));
代码语言：javascript复制private static final class RMAppNewlySavingTransition extends RMAppTransition {
@Override
public void transition(RMAppImpl app, RMAppEvent event) {
// If recovery is enabled then store the application information in a
// non-blocking call so make sure that RM has stored the information
// needed to restart the AM after RM restart without further client
// communication
LOG.info("Storing application with id " app.applicationId);
app.rmContext.getStateStore().storeNewApplication(app);
}
}通过事件调度器对新建Application进行处理。其实就只是对application的信息进行了保存而已。
