hadoop 2.6 AbstractYarnScheduler源代码解析

 AbstractYarnScheduler　扩展了AbstractService 实现了 ResourceScheduler 。

 SchedulerNode是AbstractYarnScheduler的一个参数化构建类，代表一个计算结点的各种属性，如下：

   availableResource：可用的资源。
   usedResource：已经使用的资源;
   totalResourceCapability：总共资源容量
   reservedContainer：保留的资源
   numContainers：正在运行的容器数。
   private final Map<ContainerId, RMContainer> launchedContainers =      new HashMap<ContainerId, RMContainer>();//已经启动了的容器映射。
   private final RMNode rmNode;//Node Manager的相关信息
   private final String nodeName;//结点名称
   private volatile Set<String> labels = null; //结点标签

RMNode 是一个接口，有以下内容：

public interface RMNode {

  /** negative value means no timeout */
  public static final int OVER_COMMIT_TIMEOUT_MILLIS_DEFAULT = -1;//如果此值为负，代表永不超时。
  
  /**
   * the node id of of this node.
   * @return the node id of this node.
   */
  public NodeId getNodeID();//结点ID
  
  /**
   * the hostname of this node
   * @return hostname of this node
   */
  public String getHostName();//主机名
  
  /**
   * the command port for this node
   * @return command port for this node
   */
  public int getCommandPort();//命令端口
  
  /**
   * the http port for this node
   * @return http port for this node
   */
  public int getHttpPort();//Http端口


  /**
   * the ContainerManager address for this node.
   * @return the ContainerManager address for this node.
   */
  public String getNodeAddress();//结点的ContainerManager地址
  
  /**
   * the http-Address for this node.
   * @return the http-url address for this node
   */
  public String getHttpAddress();//结点的http地址
  
  /**
   * the latest health report received from this node.
   * @return the latest health report received from this node.
   */
  public String getHealthReport();//健康状态报告
  
  /**
   * the time of the latest health report received from this node.
   * @return the time of the latest health report received from this node.
   */
  public long getLastHealthReportTime();//最后一次收到的健康报告时间

  /**
   * the node manager version of the node received as part of the
   * registration with the resource manager
   */
  public String getNodeManagerVersion();//node manager的版本

  /**
   * the total available resource.
   * @return the total available resource.
   */
  public Resource getTotalCapability();
  
  /**
   * The rack name for this node manager.
   * @return the rack name.
   */
  public String getRackName();
  
  /**
   * the {@link Node} information for this node.
   * @return {@link Node} information for this node.
   */
  public Node getNode();
  
  public NodeState getState();

  public List<ContainerId> getContainersToCleanUp();

  public List<ApplicationId> getAppsToCleanup();

  /**
   * Update a {@link NodeHeartbeatResponse} with the list of containers and
   * applications to clean up for this node.
   * @param response the {@link NodeHeartbeatResponse} to update
   */
  public void updateNodeHeartbeatResponseForCleanup(NodeHeartbeatResponse response);

  public NodeHeartbeatResponse getLastNodeHeartBeatResponse();

  /**
   * Reset lastNodeHeartbeatResponse's ID to 0.
   */
  void resetLastNodeHeartBeatResponse();

  /**
   * Get and clear the list of containerUpdates accumulated across NM
   * heartbeats.
   * 
   * @return containerUpdates accumulated across NM heartbeats.
   */
  public List<UpdatedContainerInfo> pullContainerUpdates();
  
  /**
   * Get set of labels in this node
   * 
   * @return labels in this node
   */
  public Set<String> getNodeLabels();
}

NodeState是结点状态的枚举

public enum NodeState {
  /** New node */
  NEW, 
  
  /** Running node */
  RUNNING, 
  
  /** Node is unhealthy */
  UNHEALTHY, 
  
  /** Node is out of service */
  DECOMMISSIONED, 
  
  /** Node has not sent a heartbeat for some configured time threshold*/
  LOST, 
  
  /** Node has rebooted */
  REBOOTED;
  
  public boolean isUnusable() {
    return (this == UNHEALTHY || this == DECOMMISSIONED || this == LOST);
  }
}

NodeHeartbeatResponse

public interface NodeHeartbeatResponse {
  int getResponseId();
  NodeAction getNodeAction(); NodeAction是一个枚举，有三种状态  NORMAL, RESYNC, SHUTDOWN

  List<ContainerId> getContainersToCleanup();
  List<ContainerId> getContainersToBeRemovedFromNM();

  List<ApplicationId> getApplicationsToCleanup();

  void setResponseId(int responseId);
  void setNodeAction(NodeAction action);

  MasterKey getContainerTokenMasterKey();
  void setContainerTokenMasterKey(MasterKey secretKey);
  
  MasterKey getNMTokenMasterKey();
  void setNMTokenMasterKey(MasterKey secretKey);

  void addAllContainersToCleanup(List<ContainerId> containers);

  // This tells NM to remove finished containers from its context. Currently, NM
  // will remove finished containers from its context only after AM has actually
  // received the finished containers in a previous allocate response
  void addContainersToBeRemovedFromNM(List<ContainerId> containers);
  
  void addAllApplicationsToCleanup(List<ApplicationId> applications);

  long getNextHeartBeatInterval();
  void setNextHeartBeatInterval(long nextHeartBeatInterval);
  
  String getDiagnosticsMessage();

  void setDiagnosticsMessage(String diagnosticsMessage);

  // Credentials (i.e. hdfs tokens) needed by NodeManagers for application
  // localizations and logAggreations.
  Map<ApplicationId, ByteBuffer> getSystemCredentialsForApps();

  void setSystemCredentialsForApps(
      Map<ApplicationId, ByteBuffer> systemCredentials);
}

SchedulerApplication 有以下三个主要字段：

  private Queue queue;
  private final String user;
  private T currentAttempt;