public void runMainLoop() throws Exception {
rmClient.registerApplicationMaster("", 0, "");
initRegistry();
startMasterNode();
Priority priority = Records.newRecord(Priority.class);
priority.setPriority(0);
Resource capability = Records.newRecord(Resource.class);
capability.setMemory(ClusterConf.get().getWorkerHeapSize());
capability.setVirtualCores(ClusterConf.get().getNumWorkerThreads());
List<ContainerRequest> containerReq = new ArrayList<ContainerRequest>();
for (int i = 0; i < ClusterConf.get().getNumWorkers(); ++i) {
ContainerRequest containerAsk = new ContainerRequest(capability, null, null, priority);
rmClient.addContainerRequest(containerAsk);
containerReq.add(containerAsk);
}
while (alive) {
Thread.sleep(1000);
}
finish();
/*
for (ContainerRequest req : containerReq) {
rmClient.removeContainerRequest(req);
}
int containersToAdd = 2;
numContainersToWaitFor = containersToAdd;
System.out.println("[Am] finished all containers. Asking for more containers, total=" + numContainersToWaitFor);
for (int i = 0; i < containersToAdd; ++i) {
ContainerRequest containerAsk = new ContainerRequest(capability, null, null, priority);
System.out.println("[AM] Making res-req " + i);
rmClient.addContainerRequest(containerAsk);
}
System.out.println("[AM] waiting for containers to finish once more!!!");
while (!doneWithContainers()) {
Thread.sleep(100);
}
*/
}
/**
* Main run function for the application master
*
* @throws YarnException
* @throws IOException
*/
@SuppressWarnings({"unchecked"})
public void run() throws YarnException, IOException {
LOG.info("Starting ApplicationMaster");
try {
publishApplicationAttemptEvent(
timelineClient, appAttemptID.toString(), DSEvent.DS_APP_ATTEMPT_START);
} catch (Exception e) {
LOG.error("App Attempt start event coud not be pulished for " + appAttemptID.toString(), e);
}
Credentials credentials = UserGroupInformation.getCurrentUser().getCredentials();
DataOutputBuffer dob = new DataOutputBuffer();
credentials.writeTokenStorageToStream(dob);
// Now remove the AM->RM token so that containers cannot access it.
Iterator<Token<?>> iter = credentials.getAllTokens().iterator();
LOG.info("Executing with tokens:");
while (iter.hasNext()) {
Token<?> token = iter.next();
LOG.info(token);
if (token.getKind().equals(AMRMTokenIdentifier.KIND_NAME)) {
iter.remove();
}
}
allTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength());
// Create appSubmitterUgi and add original tokens to it
String appSubmitterUserName = System.getenv(ApplicationConstants.Environment.USER.name());
appSubmitterUgi = UserGroupInformation.createRemoteUser(appSubmitterUserName);
appSubmitterUgi.addCredentials(credentials);
AMRMClientAsync.CallbackHandler allocListener = new RMCallbackHandler();
amRMClient = AMRMClientAsync.createAMRMClientAsync(1000, allocListener);
amRMClient.init(conf);
amRMClient.start();
containerListener = createNMCallbackHandler();
nmClientAsync = new NMClientAsyncImpl(containerListener);
nmClientAsync.init(conf);
nmClientAsync.start();
// Setup local RPC Server to accept status requests directly from clients
// TODO need to setup a protocol for client to be able to communicate to
// the RPC server
// TODO use the rpc port info to register with the RM for the client to
// send requests to this app master
// Register self with ResourceManager
// This will start heartbeating to the RM
appMasterHostname = NetUtils.getHostname();
RegisterApplicationMasterResponse response =
amRMClient.registerApplicationMaster(
appMasterHostname, appMasterRpcPort, appMasterTrackingUrl);
// Dump out information about cluster capability as seen by the
// resource manager
int maxMem = response.getMaximumResourceCapability().getMemory();
LOG.info("Max mem capabililty of resources in this cluster " + maxMem);
int maxVCores = response.getMaximumResourceCapability().getVirtualCores();
LOG.info("Max vcores capabililty of resources in this cluster " + maxVCores);
// A resource ask cannot exceed the max.
if (containerMemory > maxMem) {
LOG.info(
"Container memory specified above max threshold of cluster."
+ " Using max value."
+ ", specified="
+ containerMemory
+ ", max="
+ maxMem);
containerMemory = maxMem;
}
if (containerVirtualCores > maxVCores) {
LOG.info(
"Container virtual cores specified above max threshold of cluster."
+ " Using max value."
+ ", specified="
+ containerVirtualCores
+ ", max="
+ maxVCores);
containerVirtualCores = maxVCores;
}
List<Container> previousAMRunningContainers = response.getContainersFromPreviousAttempts();
LOG.info(
"Received "
+ previousAMRunningContainers.size()
+ " previous AM's running containers on AM registration.");
numAllocatedContainers.addAndGet(previousAMRunningContainers.size());
int numTotalContainersToRequest = numTotalContainers - previousAMRunningContainers.size();
// Setup ask for containers from RM
// Send request for containers to RM
// Until we get our fully allocated quota, we keep on polling RM for
// containers
// Keep looping until all the containers are launched and shell script
// executed on them ( regardless of success/failure).
for (int i = 0; i < numTotalContainersToRequest; ++i) {
ContainerRequest containerAsk = setupContainerAskForRM();
amRMClient.addContainerRequest(containerAsk);
}
numRequestedContainers.set(numTotalContainersToRequest);
try {
publishApplicationAttemptEvent(
timelineClient, appAttemptID.toString(), DSEvent.DS_APP_ATTEMPT_END);
} catch (Exception e) {
LOG.error("App Attempt start event coud not be pulished for " + appAttemptID.toString(), e);
}
}
