Hadoop Yarn 3.1.0 源码分析 （03 容器分配和投运）

接下来我们看容器的分配和在NM节点上的投运过程，接着上一篇：
FairScheduler.handle() -> FairScheduler.nodeUpdate() -> FairScheduler.attemptScheduling() -> queueMgr.getRootQueue().assignContainer():

public Resource assignContainer(FSSchedulerNode node) {
    Resource assigned = Resources.none();

    // If this queue is over its limit, reject
    if (!assignContainerPreCheck(node)) {
      return assigned;
    }

    // 根据FairScheduler的调度规则对子队列进行排序
    writeLock.lock();
    try {
      Collections.sort(childQueues, policy.getComparator());
    } finally {
      writeLock.unlock();
    }

    readLock.lock();
    try {
      for (FSQueue child : childQueues) {
        assigned = child.assignContainer(node);
        if (!Resources.equals(assigned, Resources.none())) {
          break;
        }
      }
    } finally {
      readLock.unlock();
    }
    return assigned;
  }

FairScheduler.handle() -> FairScheduler.nodeUpdate() -> FairScheduler.attemptScheduling() -> queueMgr.getRootQueue().assignContainer() -> FSLeafQueue.assignContainer()

 public Resource assignContainer(FSSchedulerNode node) {
    Resource assigned = none();
    if (LOG.isDebugEnabled()) {
      LOG.debug("Node " + node.getNodeName() + " offered to queue: " +
          getName() + " fairShare: " + getFairShare());
    }

    if (!assignContainerPreCheck(node)) {
      return assigned;
    }

    for (FSAppAttempt sched : fetchAppsWithDemand(true)) {
      if (SchedulerAppUtils.isPlaceBlacklisted(sched, node, LOG)) {
        continue;
      }
      assigned = sched.assignContainer(node);
      if (!assigned.equals(none())) {
        if (LOG.isDebugEnabled()) {
          LOG.debug("Assigned container in queue:" + getName() + " " +
              "container:" + assigned);
        }
        break;
      }
    }
    return assigned;
  }

从根队列然后到子队列，最后到子队列中按照调度规则，应该被调度用于分配容器的应用程序的实例进行容器分配。
FairScheduler.handle() -> FairScheduler.nodeUpdate() -> FairScheduler.attemptScheduling() -> queueMgr.getRootQueue().assignContainer() -> FSLeafQueue.assignContainer() -> FSAppAttempt.assignContainer():

 public Resource assignContainer(FSSchedulerNode node) {
    if (isOverAMShareLimit()) {
      PendingAsk amAsk = appSchedulingInfo.getNextPendingAsk();
      updateAMDiagnosticMsg(amAsk.getPerAllocationResource(),
          " exceeds maximum AM resource allowed).");
      if (LOG.isDebugEnabled()) {
        LOG.debug("AM resource request: " + amAsk.getPerAllocationResource()
            + " exceeds maximum AM resource allowed, "
            + getQueue().dumpState());
      }
      return Resources.none();
    }
    return assignContainer(node, false);
  }

 private Resource assignContainer(FSSchedulerNode node, boolean reserved) {
    if (LOG.isTraceEnabled()) {
      LOG.trace("Node offered to app: " + getName() + " reserved: " + reserved);
    }

    Collection<SchedulerRequestKey> keysToTry = (reserved) ?
        Collections.singletonList(
            node.getReservedContainer().getReservedSchedulerKey()) :
        getSchedulerKeys();
    //对于应用中的每一种优先级请求，看是否满足NODE_LOCAL,RACK_LOCAL,OFF_SWITCH这三种本地性需求
    //请求可能被延迟调度，如果设置了延期调度参数来提升本地性
    try {
      writeLock.lock();
      for (SchedulerRequestKey schedulerKey : keysToTry) {

        if (!reserved && !hasContainerForNode(schedulerKey, node)) {
          continue;
        }

        addSchedulingOpportunity(schedulerKey);