java线程池ThreadPoolExecutor类核心方法理解

java线程池ThreadPoolExecutor类核心方法理解

李老爷子的注释其实已经非常详细了,这里主要是将逐句意义和我自己的理解贴出来.

本文不涉及ctl状态的二进制算法的理解(在此无意义).

完整构造线程池

/**
 * Creates a new {@code ThreadPoolExecutor} with the given initial
 * parameters.
 *
 * @param corePoolSize the number of threads to keep in the pool, even
 *        if they are idle, unless {@code allowCoreThreadTimeOut} is set
 * @param maximumPoolSize the maximum number of threads to allow in the
 *        pool
 * @param keepAliveTime when the number of threads is greater than
 *        the core, this is the maximum time that excess idle threads
 *        will wait for new tasks before terminating.
 * @param unit the time unit for the {@code keepAliveTime} argument
 * @param workQueue the queue to use for holding tasks before they are
 *        executed.  This queue will hold only the {@code Runnable}
 *        tasks submitted by the {@code execute} method.
 * @param threadFactory the factory to use when the executor
 *        creates a new thread
 * @param handler the handler to use when execution is blocked
 *        because the thread bounds and queue capacities are reached
 * @throws IllegalArgumentException if one of the following holds:<br>
 *         {@code corePoolSize < 0}<br>
 *         {@code keepAliveTime < 0}<br>
 *         {@code maximumPoolSize <= 0}<br>
 *         {@code maximumPoolSize < corePoolSize}
 * @throws NullPointerException if {@code workQueue}
 *         or {@code threadFactory} or {@code handler} is null
 */
public ThreadPoolExecutor(int corePoolSize,//核心线程数(核心线程不会被销毁)
                          int maximumPoolSize,//最大线程数
                          long keepAliveTime,//超过核心线程数的线程的最大空闲生存时间,其后将可能被销毁
                          TimeUnit unit,//keepAliveTime的单位
                          BlockingQueue<Runnable> workQueue,//线程队列,当线程数超过核心线程数时入队
                          ThreadFactory threadFactory,//线程工厂
                          RejectedExecutionHandler handler//当线程数满,队列满时的拒绝策略
                         ) {
    if (corePoolSize < 0 ||
            maximumPoolSize <= 0 ||
            maximumPoolSize < corePoolSize ||
            keepAliveTime < 0)
        throw new IllegalArgumentException();
    if (workQueue == null || threadFactory == null || handler == null)
        throw new NullPointerException();
    this.corePoolSize = corePoolSize;
    this.maximumPoolSize = maximumPoolSize;
    this.workQueue = workQueue;
    this.keepAliveTime = unit.toNanos(keepAliveTime);
    this.threadFactory = threadFactory;
    this.handler = handler;
}

ThreadPoolExecutor::submit

//提交一个允许有返回值的任务,Future::get获取返回值.
public Future<?> submit(Runnable task) {
    if (task == null) throw new NullPointerException();
    //RunnableFuture自己就是一个Runnable且同时是一个Future可以用来接收返回值
    RunnableFuture<Void> ftask = newTaskFor(task, null);
    //执行execute,添加woker运行指定task
    execute(ftask);
    return ftask;
}

ThreadPoolExecutor::execute

/**
* Executes the given task sometime in the future.  The task
* may execute in a new thread or in an existing pooled thread.
*
* If the task cannot be submitted for execution, either because this
* executor has been shutdown or because its capacity has been reached,
* the task is handled by the current {@link RejectedExecutionHandler}.
*
* @param command the task to execute
* @throws RejectedExecutionException at discretion of
*         {@code RejectedExecutionHandler}, if the task
*         cannot be accepted for execution
* @throws NullPointerException if {@code command} is null
*/
public void execute(Runnable command) {
	if (command == null)
		throw new NullPointerException();
    /*
     * Proceed in 3 steps:
     *
     * 1. If fewer than corePoolSize threads are running, try to
     * start a new thread with the given command as its first
     * task.  The call to addWorker atomically checks runState and
     * workerCount, and so prevents false alarms that would add
     * threads when it shouldn't, by returning false.
     *
     * 2. If a task can be successfully queued, then we still need
     * to double-check whether we should have added a thread
     * (because existing ones died since last checking) or that
     * the pool shut down since entry into this method. So we
     * recheck state and if necessary roll back the enqueuing if
     * stopped, or start a new thread if there are none.
     *
     * 3. If we cannot queue task, then we try to add a new
     * thread.  If it fails, we know we are shut down or saturated
     * and so reject the task.
     */
	/*
    * 分三步进行:
    * 1. 如果运行的线程少于corePoolSize,
    * 尝试以command作为第一个task开启一个一个新核心线程.
    * 2. 如果成功将command入队workQueue,
    * 双重检测确保线程池正RUNNING,
    * (可能有其他线程执行了shutdown).
    * 如果线程池已经shutdown,则回滚入队操作,
    * 并执行拒绝策略
    * 3. 如果无法入队,直接添加新的工作线程并执行command,
    * 如果操作失败了,则说明线程池可能已经shutdown或饱和了,
    * 则执行拒绝策略
    */
    // 也就是说:1.如果核心线程没满开核心线程,否则将任务加入任务队列,
    // 2.如果此时线程池关了,出队任务并执行拒绝策略
    // 3.如果核心线程设定为且工作线程为0,则开非核心线程并执行队列中的任务,
    // 4.如果队列满了开非核心线程,如果失败了执行拒绝策略
    // 即:1.如果核心线程数设定大于0,只要任务队列没满就最多只会有核心线程.
    // 2.如果核心线程数设定等于0,只要任务队列没满就最多只有一个非核心线程.
	//获取ctl快照
	int c = ctl.get();
	//第一步
	//判断工作线程数是否少于设定的核心线程数值
	if (workerCountOf(c) < corePoolSize) {
		//添加核心工作线程
		if (addWorker(command, true))
			return;
		//重新获取ctl快照(ctl可能已被其他线程修改)
		c = ctl.get();
	}
	//第二部
	//如果线程池正RUNNING,将command加入workQueue
	if (isRunning(c) && workQueue.offer(command)) {
		//重新获取ctl快照
		int recheck = ctl.get();
		//双重检测,确保线程池没有shutdown,如果shutdown了则将command出队workQueue
		if (! isRunning(recheck) && remove(command))
			//执行拒绝策略
			reject(command);
		//判断此时线程池正RUNNING,且工作线程为0(corePoolSize可被设定为0)
		else if (workerCountOf(recheck) == 0)
			//添加非核心线程,并从workQueue中取出首个command运行
			addWorker(null, false);
	}
	//队列可能已满从而失败的情况下,直接添加非核心工作线程,并将command作为task运行
	else if (!addWorker(command, false))
		//执行addWorker失败(线程池关闭或饱和)则执行拒绝策略
		reject(command);
}

ThreadPoolExecutor::addWorker

/*
* Methods for creating, running and cleaning up after workers
*/

/**
* Checks if a new worker can be added with respect to current
* pool state and the given bound (either core or maximum). If so,
* the worker count is adjusted accordingly, and, if possible, a
* new worker is created and started, running firstTask as its
* first task. This method returns false if the pool is stopped or
* eligible to shut down. It also returns false if the thread
* factory fails to create a thread when asked.  If the thread
* creation fails, either due to the thread factory returning
* null, or due to an exception (typically OutOfMemoryError in
* Thread.start()), we roll back cleanly.
*
* @param firstTask the task the new thread should run first (or
* null if none). Workers are created with an initial first task
* (in method execute()) to bypass queuing when there are fewer
* than corePoolSize threads (in which case we always start one),
* or when the queue is full (in which case we must bypass queue).
* Initially idle threads are usually created via
* prestartCoreThread or to replace other dying workers.
*
* @param core if true use corePoolSize as bound, else
* maximumPoolSize. (A boolean indicator is used here rather than a
* value to ensure reads of fresh values after checking other pool
* state).
* @return true if successful
*/
private boolean addWorker(Runnable firstTask, boolean core) {
    retry:
    for (int c = ctl.get();;) {//死循环,每次循环获取ctl最新快照
        // Check if queue empty only if necessary.
        // 必要时检测workQueue是否为空.(这里利用与或行为的短路一层一层判断)
        // 什么是必要条件:当且仅当线程池被SHUTDOWN的时候,且不再有新任务.
        // 即:addWorker时,如果线程池已经SHUTDOWN就不再接受新任务,但继续消费workQueue中的任务.
        if (
            //1.检测线程是否已经被SHUTDOWN,如果此时还是RUNNING就直接执内循环,否则如果至少是SHUTDOWN则进入下个与(进入下一个与线程池至少SHUTDOWN,甚至是STOP)
            runStateAtLeast(c, SHUTDOWN)
            && (
                //2.1.检查线程是否已经被STOP,如果被STOP了就不再消费workQueue,返回false,如果小于STOP则进入下一个或(进入下一个或线程池必然处在SHUTDOWN)
                runStateAtLeast(c, STOP)
                //2.2.如果有指定要执行的任务,由于此时线程池已经SHUTDOWN,不接收新任务,直接返回false,如果没给定新任务则进入下一个或
                || firstTask != null
                //2.3. 如果任务队列为空,此时线程池也正处在SHUTDOWN,同时也没有新任务,则返回false,否则需要进入内循环消费workQueue剩余任务
                || workQueue.isEmpty()
            )
        )
            //执行失败(三种情况:1.线程池已经STOP,2.线城池是SHUTDOWN但指定了新任务,3.线城池是SHUTDOWN且workQueue为空)
            return false;

        for (;;) {
            //当前线程数:1.如果是add核心线程,判断是否大于等于核心线程数,否则判断是否大于等于最大线程数
            if (workerCountOf(c)
                >= ((core ? corePoolSize : maximumPoolSize) & COUNT_MASK))
                //线程池饱和,执行失败
                return false;
            //上面判断都过了,说明此时可以添加任务,CAS先将线程数加一(如果后面实际添加worker执行失败再回退),CAS执行成功则跳出外循环,执行下面的添加worker
            if (compareAndIncrementWorkerCount(c))
                break retry;
            //重新获取ctl快照,确保获取到的是最新的值(值传递)
            c = ctl.get();  // Re-read ctl
            //如果此时状态至少是SHUTDOWN,则重新执行外循环
            if (runStateAtLeast(c, SHUTDOWN))
                continue retry;
            // else CAS failed due to workerCount change; retry inner loop
            // 否则,重新执行内循环将线程数加一
        }
    }

    boolean workerStarted = false;
    boolean workerAdded = false;
    Worker w = null;
    try {
        //新建worker,并将firstTask丢进入,以保证如果有firstTask的情况下它会最先执行
        //内部线程的run方法会runWorker方法,runWorker会循环从workQueue取任务执行
        w = new Worker(firstTask);
        //拿到worker内部新建的线程快照
        final Thread t = w.thread;
        if (t != null) {
            final ReentrantLock mainLock = this.mainLock;
            //这里的操作需要加锁主要是因为workers是HashSet,线程不安全
            mainLock.lock();
            try {
                // Recheck while holding lock.
                // Back out on ThreadFactory failure or if
                // shut down before lock acquired.
                // 在获得锁后重新检测,以确保线程池正处在正常运行状态
                // 重新获取最新快照
                int c = ctl.get();

                //如果正RUNNING,则直接添加worker到集合中
                if (isRunning(c) ||
                    //否则如果线程池是SHUTDOWN且没有新任务的情况下才添加worker到集合中
                    (runStateLessThan(c, STOP) && firstTask == null)) {
                    //如果线程不是处与新建状态,抛出异常(因为后面会执行start)
                    if (t.getState() != Thread.State.NEW)
                        throw new IllegalThreadStateException();
                    //添加worker到集合中
                    workers.add(w);
                    //修改worker添加状态
                    workerAdded = true;
                    //修改总worker数量
                    int s = workers.size();
                    if (s > largestPoolSize)
                        largestPoolSize = s;
                }
            } finally {
                //解锁
                mainLock.unlock();
            }
            //如果已经添加了worker,说明此时worker创建成功,且内部的线程没有开始运行,则使其运行
            if (workerAdded) {
                t.start();
                //修改worker启动状态
                workerStarted = true;
            }
        }
    } finally {
        //如果worker线程被启动失败
        if (! workerStarted)
            //回退上面的工作线程数加一操作,并将worker从集合中移除(如果worker已经被加入了集合的话),并执行tryTerminate内部的terminated钩子
            addWorkerFailed(w);
    }
    return workerStarted;
}

ThreadPoolExecutor::runWorker

/**
 * Main worker run loop.  Repeatedly gets tasks from queue and
 * executes them, while coping with a number of issues:
 *
 * 1. We may start out with an initial task, in which case we
 * don't need to get the first one. Otherwise, as long as pool is
 * running, we get tasks from getTask. If it returns null then the
 * worker exits due to changed pool state or configuration
 * parameters.  Other exits result from exception throws in
 * external code, in which case completedAbruptly holds, which
 * usually leads processWorkerExit to replace this thread.
 *
 * 2. Before running any task, the lock is acquired to prevent
 * other pool interrupts while the task is executing, and then we
 * ensure that unless pool is stopping, this thread does not have
 * its interrupt set.
 *
 * 3. Each task run is preceded by a call to beforeExecute, which
 * might throw an exception, in which case we cause thread to die
 * (breaking loop with completedAbruptly true) without processing
 * the task.
 *
 * 4. Assuming beforeExecute completes normally, we run the task,
 * gathering any of its thrown exceptions to send to afterExecute.
 * We separately handle RuntimeException, Error (both of which the
 * specs guarantee that we trap) and arbitrary Throwables.
 * Because we cannot rethrow Throwables within Runnable.run, we
 * wrap them within Errors on the way out (to the thread's
 * UncaughtExceptionHandler).  Any thrown exception also
 * conservatively causes thread to die.
 *
 * 5. After task.run completes, we call afterExecute, which may
 * also throw an exception, which will also cause thread to
 * die. According to JLS Sec 14.20, this exception is the one that
 * will be in effect even if task.run throws.
 *
 * The net effect of the exception mechanics is that afterExecute
 * and the thread's UncaughtExceptionHandler have as accurate
 * information as we can provide about any problems encountered by
 * user code.
 *
 * @param w the worker
 */
/*
这个线程的核心是while循环不停的从队列中拿取任务并在独占锁的情况下执行(不会被中断)
线程被终止的情况:
1. 当执行的任务抛出异常线程将终止(线程池还在运行时将有新线程替代它);
2. 非核心线程在等待任务到超时后被通过中断终止;
3. 线程池停止时中断自己或被中断.
线程自己中断的条件:线程池已经至少是STOP,且当前线程没被中断过
判单当前线程是否空闲:在while循环中是会上锁的,而在getTask等待的过程中没有,
此时其他线程通过tryLock如果获取到了锁则说明线程当前处于空闲状态,
这种方式还可以保证其他线程在判断到当前线程是空闲时,当前线程不会被getTask从阻塞中唤醒并执行task
*/
final void runWorker(Worker w) {
    Thread wt = Thread.currentThread();
    //拿到指定的firstTask先执行并清空firstTask
    Runnable task = w.firstTask;
    w.firstTask = null;
    w.unlock(); // allow interrupts 允许中断
    boolean completedAbruptly = true;
    try {
        //当没有firstTask的时候阻塞地等待获取task
        while (task != null || (task = getTask()) != null) {
            //拿到task了就上锁,主要目的用来在其他线程判断当前线程是否还在阻塞等待获取task
            w.lock();
            // If pool is stopping, ensure thread is interrupted;
            // if not, ensure thread is not interrupted.  This
            // requires a recheck in second case to deal with
            // shutdownNow race while clearing interrupt
            // 如果线程池处在执行停止方法,确保线程已被中断;
            // 否则,确保线程没有被中断.
            // 这种情况下需要在shutdownNow方法中双重检测以清理(处理)中断.
            // 这里的if需要完成的任务: 如果线程池的状态至少是STOP状态,则要保证当前线程已经被执行过中断,
            // 没有的话就立刻执行中断,后面的task将不会执行,这种情况可能时执行了shutdownNow方法.
            if (
                (
                    //1.1.当线程池已经至少时STOP状态  或
                    runStateAtLeast(ctl.get(), STOP) ||
                    (
                        //2.1.当前线程线程已经被中断(如果中断这个方法内部执行clearInterruptEvent)  且 
                        Thread.interrupted() &&
                        //2.2.线程池已经至少时STOP状态
                        runStateAtLeast(ctl.get(), STOP)
                    )
                ) &&
                //1.2.线程未被中断
                !wt.isInterrupted()
            )
                //中断线程,下面的try将不再被执行
                wt.interrupt();
            try {
                //执行钩子方法beforeExecute
                beforeExecute(wt, task);
                try {
                    task.run();
                    ////执行钩子方法afterExecute(无异常)
                    afterExecute(task, null);
                } catch (Throwable ex) {
                    //执行钩子方法afterExecute(异常)
                    afterExecute(task, ex);
                    //将异常抛出,这意味这个线程将消亡,如果线程池还在运行,将有新的线程替代它
                    throw ex;
                }
            } finally {
                //清除已经执行的task引用
                task = null;
                //当前线程完成任务数+1
                w.completedTasks++;
                //解锁,则说明线程又进入空闲状态
                w.unlock();
            }
        }
        //如果循环内抛出了异常,这里将不会执行
        completedAbruptly = false;
    } finally {
        //执行线程退出的方法,当执行到这里线程说明线程即将消亡(非核心线程超时或线程任务执行抛出了异常或线程池将停止)
        processWorkerExit(w, completedAbruptly);
    }
}

ThreadPoolExecutor::beforeExecute和afterExecute模板方法(钩子方法)

//钩子方法只在runWorker中执行
//继承ThreadPoolExecutor以实现钩子方法
class MyThreadPoolExecutor extends ThreadPoolExecutor {
    public MyThreadPoolExecutor(int corePoolSize, int maximumPoolSize, long keepAliveTime, TimeUnit unit, BlockingQueue<Runnable> workQueue, ThreadFactory threadFactory, RejectedExecutionHandler handler) {
        super(corePoolSize, maximumPoolSize, keepAliveTime, unit, workQueue, threadFactory, handler);
    }
    @Override
    //runWorker内部执行task.run()前执行这个钩子方法
    protected void beforeExecute(Thread t, Runnable r) {
        super.beforeExecute(t, r);
        System.out.println("执行任务前的钩子,已执行"+this.getTaskCount());
    }
    @Override
    //runWorker内部执行task.run()后执行这个钩子方法,如果run抛出了异常可以在此处理
    protected void afterExecute(Runnable r, Throwable t) {
        super.afterExecute(r, t);
        System.out.println("执行任务后的钩子,完成执行"+this.getTaskCount());
    }
}

ThreadPoolExecutor::processWorkerExit

/**
 * Performs cleanup and bookkeeping for a dying worker. Called
 * only from worker threads. Unless completedAbruptly is set,
 * assumes that workerCount has already been adjusted to account
 * for exit.  This method removes thread from worker set, and
 * possibly terminates the pool or replaces the worker if either
 * it exited due to user task exception or if fewer than
 * corePoolSize workers are running or queue is non-empty but
 * there are no workers.
 *
 * @param w the worker
 * @param completedAbruptly if the worker died due to user exception
 */
/*
线程退方法只在runWorker最后执行
主要完成一些清理工作(将当前线程从池中移除)和记录工作(当前线程的)
如果线程池还在运行,将可能添加新线程替代这个线程(此时这个线程可能在执行中抛出了异常
*/
private void processWorkerExit(Worker w, boolean completedAbruptly) {
    //如果completedAbruptly为true,则说明runWorker中task.run没执行(此时这个方法是在中断时执行)或runWorker的while循环中抛出了异常
    if (completedAbruptly) // If abrupt, then workerCount wasn't adjusted
        decrementWorkerCount();//这种情况工作线程数还没被减一,在此减一

    final ReentrantLock mainLock = this.mainLock;
    mainLock.lock();//上锁以线性执行,保障workers和completedTaskCount不会混乱
    try {
        completedTaskCount += w.completedTasks;//将当前线程的任务完成数加到线程池
        workers.remove(w);//把当前线程从works中移除
    } finally {
        mainLock.unlock();
    }

    //执行tryTerminate清理线程并在其内部执行terminated钩子
    tryTerminate();

    int c = ctl.get();//获取ctl快照
    //如线程还没进入STOP(处在RUNNING或SHUTDOWN)
    if (runStateLessThan(c, STOP)) {
        //如果不是被突然终止(即task.run及其钩子执行成功,没抛出异常的情况下)
        if (!completedAbruptly) {
            //拿到最小线程数
            int min = allowCoreThreadTimeOut ? 0 : corePoolSize;
            //如果最小线程数为0,但此时工作队列内还有task,将最小线程数设置为1保证有线程执行队列中的task
            if (min == 0 && ! workQueue.isEmpty())
                min = 1;
            //如果当前存在的工作线程数大于等于最小线程数就不用添加新线程,否则就添加一个线程执行队列中的task
            if (workerCountOf(c) >= min)
                return; // replacement not needed
        }
        //否则(即task.run及其钩子没执行或抛出异常的情况下)
        addWorker(null, false);//添加一个新的工作线程替代此线程
    }
}

ThreadPoolExecutor::tryTerminate

/**
 * Transitions to TERMINATED state if either (SHUTDOWN and pool
 * and queue empty) or (STOP and pool empty).  If otherwise
 * eligible to terminate but workerCount is nonzero, interrupts an
 * idle worker to ensure that shutdown signals propagate. This
 * method must be called following any action that might make
 * termination possible -- reducing worker count or removing tasks
 * from the queue during shutdown. The method is non-private to
 * allow access from ScheduledThreadPoolExecutor.
 */
/*
这种方法被多个方法调用,主要是保证清理工作的正常进行,空闲的线程能被正常清除,
同时又至少保留一个线程以保证有线程能执行清理.
保证线程池的ctl被正确设置.
为什么在清理空闲线程时只清理一个?
因为需要保证至少留有一个线程善后,一个一个的清理能保证最后一个线程一定可以善后
(如过中断全部,由于此时没有上锁,其他线程也可以中断当前线程,可能就没线程了)
*/
final void tryTerminate() {
    //CAS死循环,不执行成功誓不罢休
    for (;;) {
        int c = ctl.get();//ctl快照
        //如果 线程正在运行  或
        if (isRunning(c) ||
                //线程已经是TIDYING或TERMINATED  或
                //(这种情况下清理工作已经做完了)
                runStateAtLeast(c, TIDYING) ||
                //线程是RUNNING或SHUTDOWN  且  工作线程不为空
                //(这个状态下要保证任务能得到执行,无需清理)
                (runStateLessThan(c, STOP) && ! workQueue.isEmpty()))
            return;//则退出
        //如果还有工作线程存活,则清理一个空闲线程
        if (workerCountOf(c) != 0) { // Eligible to terminate
            interruptIdleWorkers(ONLY_ONE);
            return;
        }

        final ReentrantLock mainLock = this.mainLock;
        mainLock.lock();//上锁,保证terminated钩子和ctl正常
        try {
            //CAS的方式将状态设置为TIDYING
            if (ctl.compareAndSet(c, ctlOf(TIDYING, 0))) {
                try {
                    terminated();//执行钩子
                } finally {
                    //无论怎样,此时线程池都彻底结束了,状态设置为TERMINATED
                    ctl.set(ctlOf(TERMINATED, 0));
                    //唤醒所有执行了awaitTermination方法并阻塞的线程,让他们继续执行
                    termination.signalAll();
                }
                return;//一切都结束了,线程池完成了它的使命
            }
        } finally {
            mainLock.unlock();
        }
        // else retry on failed CAS
    }
}