Java Code Examples for org.apache.hadoop.yarn.api.protocolrecords.RegisterApplicationMasterResponse#getContainersFromPreviousAttempts()

The following examples show how to use org.apache.hadoop.yarn.api.protocolrecords.RegisterApplicationMasterResponse#getContainersFromPreviousAttempts() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: ApplicationMaster.java    From TensorFlowOnYARN with Apache License 2.0 5 votes vote down vote up
private void setupPreviousRunningContainers(RegisterApplicationMasterResponse response) {
  String containerIdStr =
      System.getenv(Environment.CONTAINER_ID.name());
  ContainerId containerId = ContainerId.fromString(containerIdStr);
  appAttemptId = containerId.getApplicationAttemptId();
  List<Container> previousAMRunningContainers =
      response.getContainersFromPreviousAttempts();
  LOG.info(appAttemptId + " received " + previousAMRunningContainers.size()
      + " previous attempts' running containers on AM registration.");
  for (Container container : previousAMRunningContainers) {
    launchedContainers.add(container.getId());
  }
  allocatedContainerNum.addAndGet(previousAMRunningContainers.size());
}
 
Example 2
Source File: ApplicationMaster.java    From big-c with Apache License 2.0 4 votes vote down vote up
@SuppressWarnings({ "unchecked" })
public void run() throws YarnException, IOException, InterruptedException {
  LOG.info("Starting ApplicationMaster");

  // Note: Credentials, Token, UserGroupInformation, DataOutputBuffer class
  // are marked as LimitedPrivate
  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();

  startTimelineClient(conf);
  if(timelineClient != null) {
    publishApplicationAttemptEvent(timelineClient, appAttemptID.toString(),
        DSEvent.DS_APP_ATTEMPT_START, domainId, appSubmitterUgi);
  }

  // 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(appAttemptID + " received " + previousAMRunningContainers.size()
    + " previous attempts' 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(numTotalContainers);
}