/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.Exception"/>
public virtual JobID GetNewJobID()
{
try
{
this.application = client.CreateApplication().GetApplicationSubmissionContext();
this.applicationId = this.application.GetApplicationId();
return(TypeConverter.FromYarn(applicationId));
}
catch (YarnException e)
{
throw new IOException(e);
}
}
/// <exception cref="System.Exception"/>
public virtual void TestGetNewApplicationOnHA()
{
ApplicationId appId = client.CreateApplication().GetApplicationSubmissionContext(
).GetApplicationId();
NUnit.Framework.Assert.IsTrue(appId != null);
NUnit.Framework.Assert.AreEqual(cluster.CreateFakeAppId(), appId);
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="Org.Apache.Hadoop.Yarn.Exceptions.YarnException"/>
public virtual bool Run()
{
Log.Info("Starting Client");
// Connect to ResourceManager
rmClient.Start();
try
{
// Create launch context for app master
Log.Info("Setting up application submission context for ASM");
ApplicationSubmissionContext appContext = rmClient.CreateApplication().GetApplicationSubmissionContext
();
ApplicationId appId = appContext.GetApplicationId();
// set the application name
appContext.SetApplicationName(appName);
// Set the priority for the application master
Priority pri = Org.Apache.Hadoop.Yarn.Util.Records.NewRecord <Priority>();
pri.SetPriority(amPriority);
appContext.SetPriority(pri);
// Set the queue to which this application is to be submitted in the RM
appContext.SetQueue(amQueue);
// Set up the container launch context for the application master
ContainerLaunchContext amContainer = Org.Apache.Hadoop.Yarn.Util.Records.NewRecord
<ContainerLaunchContext>();
appContext.SetAMContainerSpec(amContainer);
// unmanaged AM
appContext.SetUnmanagedAM(true);
Log.Info("Setting unmanaged AM");
// Submit the application to the applications manager
Log.Info("Submitting application to ASM");
rmClient.SubmitApplication(appContext);
ApplicationReport appReport = MonitorApplication(appId, EnumSet.Of(YarnApplicationState
.Accepted, YarnApplicationState.Killed, YarnApplicationState.Failed, YarnApplicationState
.Finished));
if (appReport.GetYarnApplicationState() == YarnApplicationState.Accepted)
{
// Monitor the application attempt to wait for launch state
ApplicationAttemptReport attemptReport = MonitorCurrentAppAttempt(appId, YarnApplicationAttemptState
.Launched);
ApplicationAttemptId attemptId = attemptReport.GetApplicationAttemptId();
Log.Info("Launching AM with application attempt id " + attemptId);
// launch AM
LaunchAM(attemptId);
// Monitor the application for end state
appReport = MonitorApplication(appId, EnumSet.Of(YarnApplicationState.Killed, YarnApplicationState
.Failed, YarnApplicationState.Finished));
}
YarnApplicationState appState = appReport.GetYarnApplicationState();
FinalApplicationStatus appStatus = appReport.GetFinalApplicationStatus();
Log.Info("App ended with state: " + appReport.GetYarnApplicationState() + " and status: "
+ appStatus);
bool success;
if (YarnApplicationState.Finished == appState && FinalApplicationStatus.Succeeded
== appStatus)
{
Log.Info("Application has completed successfully.");
success = true;
}
else
{
Log.Info("Application did finished unsuccessfully." + " YarnState=" + appState.ToString
() + ", FinalStatus=" + appStatus.ToString());
success = false;
}
return(success);
}
finally
{
rmClient.Stop();
}
}
/// <summary>Main run function for the client</summary>
/// <returns>true if application completed successfully</returns>
/// <exception cref="System.IO.IOException"/>
/// <exception cref="Org.Apache.Hadoop.Yarn.Exceptions.YarnException"/>
public virtual bool Run()
{
Log.Info("Running Client");
yarnClient.Start();
YarnClusterMetrics clusterMetrics = yarnClient.GetYarnClusterMetrics();
Log.Info("Got Cluster metric info from ASM" + ", numNodeManagers=" + clusterMetrics
.GetNumNodeManagers());
IList <NodeReport> clusterNodeReports = yarnClient.GetNodeReports(NodeState.Running
);
Log.Info("Got Cluster node info from ASM");
foreach (NodeReport node in 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().Count + ", queueChildQueueCount="
+ queueInfo.GetChildQueues().Count);
IList <QueueUserACLInfo> listAclInfo = yarnClient.GetQueueAclsInfo();
foreach (QueueUserACLInfo aclInfo in listAclInfo)
{
foreach (QueueACL userAcl in aclInfo.GetUserAcls())
{
Log.Info("User ACL Info for Queue" + ", queueName=" + aclInfo.GetQueueName() + ", userAcl="
+ userAcl.ToString());
}
}
if (domainId != null && domainId.Length > 0 && toCreateDomain)
{
PrepareTimelineDomain();
}
// Get a new application id
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
IDictionary <string, LocalResource> localResources = new Dictionary <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 = string.Empty;
long hdfsShellScriptLen = 0;
long hdfsShellScriptTimestamp = 0;
if (!shellScriptPath.IsEmpty())
{
Path shellSrc = new Path(shellScriptPath);
string shellPathSuffix = appName + "/" + appId.ToString() + "/" + ScriptPath;
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");
IDictionary <string, string> env = new Dictionary <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[DSConstants.Distributedshellscriptlocation] = hdfsShellScriptLocation;
env[DSConstants.Distributedshellscripttimestamp] = System.Convert.ToString(hdfsShellScriptTimestamp
);
env[DSConstants.Distributedshellscriptlen] = System.Convert.ToString(hdfsShellScriptLen
);
if (domainId != null && domainId.Length > 0)
{
env[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(ApplicationConstants.Environment.Classpath
.$$()).Append(ApplicationConstants.ClassPathSeparator).Append("./*");
foreach (string c in conf.GetStrings(YarnConfiguration.YarnApplicationClasspath,
YarnConfiguration.DefaultYarnCrossPlatformApplicationClasspath))
{
classPathEnv.Append(ApplicationConstants.ClassPathSeparator);
classPathEnv.Append(c.Trim());
}
classPathEnv.Append(ApplicationConstants.ClassPathSeparator).Append("./log4j.properties"
);
// add the runtime classpath needed for tests to work
if (conf.GetBoolean(YarnConfiguration.IsMiniYarnCluster, false))
{
classPathEnv.Append(':');
classPathEnv.Append(Runtime.GetProperty("java.class.path"));
}
env["CLASSPATH"] = classPathEnv.ToString();
// Set the necessary command to execute the application master
Vector <CharSequence> vargs = new Vector <CharSequence>(30);
// Set java executable command
Log.Info("Setting up app master command");
vargs.AddItem(ApplicationConstants.Environment.JavaHome.$$() + "/bin/java");
// Set Xmx based on am memory size
vargs.AddItem("-Xmx" + amMemory + "m");
// Set class name
vargs.AddItem(appMasterMainClass);
// Set params for Application Master
vargs.AddItem("--container_memory " + containerMemory.ToString());
vargs.AddItem("--container_vcores " + containerVirtualCores.ToString());
vargs.AddItem("--num_containers " + numContainers.ToString());
if (null != nodeLabelExpression)
{
appContext.SetNodeLabelExpression(nodeLabelExpression);
}
vargs.AddItem("--priority " + shellCmdPriority.ToString());
foreach (KeyValuePair <string, string> entry in shellEnv)
{
vargs.AddItem("--shell_env " + entry.Key + "=" + entry.Value);
}
if (debugFlag)
{
vargs.AddItem("--debug");
}
vargs.AddItem("1>" + ApplicationConstants.LogDirExpansionVar + "/AppMaster.stdout"
);
vargs.AddItem("2>" + ApplicationConstants.LogDirExpansionVar + "/AppMaster.stderr"
);
// Get final commmand
StringBuilder command = new StringBuilder();
foreach (CharSequence str in vargs)
{
command.Append(str).Append(" ");
}
Log.Info("Completed setting up app master command " + command.ToString());
IList <string> commands = new AList <string>();
commands.AddItem(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.RmPrincipal);
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.
Org.Apache.Hadoop.Security.Token.Token <object>[] tokens = fs.AddDelegationTokens(
tokenRenewer, credentials);
if (tokens != null)
{
foreach (Org.Apache.Hadoop.Security.Token.Token <object> token in 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));
}