// 本文所有代码都引自Java 8
public final ForkJoinTask<V> fork() {
    Thread t;
    // ForkJoinWorkerThread是执行ForkJoinTask的专有线程，由ForkJoinPool管理
    // 先判断当前线程是否是ForkJoin专有线程，如果是，则将任务push到当前线程所负责的队列里去
    if ((t = Thread.currentThread()) instanceof ForkJoinWorkerThread)
        ((ForkJoinWorkerThread)t).workQueue.push(this);
    else
         // 如果不是则将线程加入队列
        // 没有显式创建ForkJoinPool的时候走这里，提交任务到默认的common线程池中
        ForkJoinPool.common.externalPush(this);
    return this;
}

public final V join() {
    int s;
    // doJoin()方法来获取当前任务的执行状态
    if ((s = doJoin() & DONE_MASK) != NORMAL)
        // 任务异常，抛出异常
        reportException(s);
    // 任务正常完成，获取返回值
    return getRawResult();
}

/**
 * doJoin()方法用来返回当前任务的执行状态
 **/
private int doJoin() {
    int s; Thread t; ForkJoinWorkerThread wt; ForkJoinPool.WorkQueue w;
    // 先判断任务是否执行完毕，执行完毕直接返回结果（执行状态）
    return (s = status) < 0 ? s :
    // 如果没有执行完毕，先判断是否是ForkJoinWorkThread线程
    ((t = Thread.currentThread()) instanceof ForkJoinWorkerThread) ?
        // 如果是，先判断任务是否处于工作队列顶端（意味着下一个就执行它）
        // tryUnpush()方法判断任务是否处于当前工作队列顶端，是返回true
        // doExec()方法执行任务
        (w = (wt = (ForkJoinWorkerThread)t).workQueue).
        // 如果是处于顶端并且任务执行完毕，返回结果
        tryUnpush(this) && (s = doExec()) < 0 ? s :
        // 如果不在顶端或者在顶端却没未执行完毕，那就调用awitJoin()执行任务
        // awaitJoin()：使用自旋使任务执行完成，返回结果
        wt.pool.awaitJoin(w, this, 0L) :
    // 如果不是ForkJoinWorkThread线程，执行externalAwaitDone()返回任务结果
    externalAwaitDone();
}

/**
     * Default ForkJoinWorkerThreadFactory implementation; creates a
     * new ForkJoinWorkerThread.
     */
    static final class DefaultForkJoinWorkerThreadFactory implements ForkJoinWorkerThreadFactory {
        public final ForkJoinWorkerThread newThread(ForkJoinPool pool) {
            return new ForkJoinWorkerThread(pool);
        }
    }

@sun.misc.Contended
public class ForkJoinPool extends AbstractExecutorService {
    // 任务队列
    volatile WorkQueue[] workQueues;   

    // 线程的运行状态
    volatile int runState;  

    // 创建ForkJoinWorkerThread的默认工厂，可以通过构造函数重写
    public static final ForkJoinWorkerThreadFactory defaultForkJoinWorkerThreadFactory;

    // 公用的线程池，其运行状态不受shutdown()和shutdownNow()的影响
    static final ForkJoinPool common;

    // 私有构造方法，没有任何安全检查和参数校验，由makeCommonPool直接调用
    // 其他构造方法都是源自于此方法
    // parallelism: 并行度，
    // 默认调用java.lang.Runtime.availableProcessors() 方法返回可用处理器的数量
    private ForkJoinPool(int parallelism,
                         ForkJoinWorkerThreadFactory factory, // 工作线程工厂
                         UncaughtExceptionHandler handler, // 拒绝任务的handler
                         int mode, // 同步模式
                         String workerNamePrefix) { // 线程名prefix
        this.workerNamePrefix = workerNamePrefix;
        this.factory = factory;
        this.ueh = handler;
        this.config = (parallelism & SMASK) | mode;
        long np = (long)(-parallelism); // offset ctl counts
        this.ctl = ((np << AC_SHIFT) & AC_MASK) | ((np << TC_SHIFT) & TC_MASK);
    }

    /**
     * Creates and returns the common pool, respecting user settings
     * specified via system properties.
     * jdk8 提供了一个简单的pool,(默认并行数是cpu核数-1), Lambda中(所有)的并行流用的就是这个方法,所以乱用并行流可能会导致线程阻塞卡死
     */
    private static ForkJoinPool makeCommonPool() {
        int parallelism = -1;
        ForkJoinWorkerThreadFactory factory = null;
        UncaughtExceptionHandler handler = null;
        try {  // ignore exceptions in accessing/parsing properties
            String pp = System.getProperty
                ("java.util.concurrent.ForkJoinPool.common.parallelism");
            String fp = System.getProperty
                ("java.util.concurrent.ForkJoinPool.common.threadFactory");
            String hp = System.getProperty
                ("java.util.concurrent.ForkJoinPool.common.exceptionHandler");
            if (pp != null)
                parallelism = Integer.parseInt(pp);
            if (fp != null)
                factory = ((ForkJoinWorkerThreadFactory)ClassLoader.
                           getSystemClassLoader().loadClass(fp).newInstance());
            if (hp != null)
                handler = ((UncaughtExceptionHandler)ClassLoader.
                           getSystemClassLoader().loadClass(hp).newInstance());
        } catch (Exception ignore) {
        }
        if (factory == null) {
            if (System.getSecurityManager() == null)
                factory = defaultForkJoinWorkerThreadFactory;
            else // use security-managed default
                factory = new InnocuousForkJoinWorkerThreadFactory();
        }
        if (parallelism < 0 && // default 1 less than #cores
            (parallelism = Runtime.getRuntime().availableProcessors() - 1) <= 0)
            parallelism = 1;
        if (parallelism > MAX_CAP)
            parallelism = MAX_CAP;
        return new ForkJoinPool(parallelism, factory, handler, LIFO_QUEUE,"ForkJoinPool.commonPool-worker-");
    }
    
}

static final int INITIAL_QUEUE_CAPACITY = 1 << 13; // 2^13 =  8192
static final int MAXIMUM_QUEUE_CAPACITY = 1 << 26; // 2^26 = 67108864

/**
     * Callback from ForkJoinWorkerThread constructor to establish and
     * record its WorkQueue.
     *
     * @param wt the worker thread
     * @return the worker's queue
     */
    final WorkQueue registerWorker(ForkJoinWorkerThread wt) {
        UncaughtExceptionHandler handler;
        wt.setDaemon(true);                           // configure thread
        if ((handler = ueh) != null)
            wt.setUncaughtExceptionHandler(handler);
        WorkQueue w = new WorkQueue(this, wt);
        int i = 0;                                    // assign a pool index
        int mode = config & MODE_MASK;
        int rs = lockRunState();
        try {
            WorkQueue[] ws; int n;                    // skip if no array
            if ((ws = workQueues) != null && (n = ws.length) > 0) {
                int s = indexSeed += SEED_INCREMENT;  // unlikely to collide
                int m = n - 1;
                i = ((s << 1) | 1) & m;               // odd-numbered indices
                if (ws[i] != null) {                  // collision
                    int probes = 0;                   // step by approx half n
                    int step = (n <= 4) ? 2 : ((n >>> 1) & EVENMASK) + 2;
                    while (ws[i = (i + step) & m] != null) {
                        if (++probes >= n) {
                            // 这里用 copyOf 进行复制, 这段代码太难读了,以后再来分析吧
                            workQueues = ws = Arrays.copyOf(ws, n <<= 1);
                            m = n - 1;
                            probes = 0;
                        }
                    }
                }
                w.hint = s;                           // use as random seed
                w.config = i | mode;
                w.scanState = i;                      // publication fence
                ws[i] = w;
            }
        } finally {
            unlockRunState(rs, rs & ~RSLOCK);
        }
        wt.setName(workerNamePrefix.concat(Integer.toString(i >>> 1)));
        return w;
    }