ThreadPoolExcutor源码分析

核心接口： Executor

public interface Executor {

/**
* Executes the given command at some time in the future.  The command
* may execute in a new thread, in a pooled thread, or in the calling
* thread, at the discretion of the {@code Executor} implementation.
*
* @param command the runnable task
* @throws RejectedExecutionException if this task cannot be
* accepted for execution
* @throws NullPointerException if command is null
*/
void execute(Runnable command);
}

execute

方法抽象为对任务（Runnable接口）的执行。

ExecutorService

接口在

Executor

的基础上提供了对任务执行的生命周期的管理，主要是

submit

和

shutdown

方法。

public interface ExecutorService extends Executor {

/**
* Initiates an orderly shutdown in which previously submitted
* tasks are executed, but no new tasks will be accepted.
* Invocation has no additional effect if already shut down.
*
* <p>This method does not wait for previously submitted tasks to
* complete execution.  Use {@link #awaitTermination awaitTermination}
* to do that.
*
* @throws SecurityException if a security manager exists and
*         shutting down this ExecutorService may manipulate
*         threads that the caller is not permitted to modify
*         because it does not hold {@link
*         java.lang.RuntimePermission}{@code ("modifyThread")},
*         or the security manager's {@code checkAccess} method
*         denies access.
*/
void shutdown();

/**
* Attempts to stop all actively executing tasks, halts the
* processing of waiting tasks, and returns a list of the tasks
* that were awaiting execution.
*
* <p>This method does not wait for actively executing tasks to
* terminate.  Use {@link #awaitTermination awaitTermination} to
* do that.
*
* <p>There are no guarantees beyond best-effort attempts to stop
* processing actively executing tasks.  For example, typical
* implementations will cancel via {@link Thread#interrupt}, so any
* task that fails to respond to interrupts may never terminate.
*
* @return list of tasks that never commenced execution
* @throws SecurityException if a security manager exists and
*         shutting down this ExecutorService may manipulate
*         threads that the caller is not permitted to modify
*         because it does not hold {@link
*         java.lang.RuntimePermission}{@code ("modifyThread")},
*         or the security manager's {@code checkAccess} method
*         denies access.
*/
List<Runnable> shutdownNow();

/**
* Returns {@code true} if this executor has been shut down.
*
* @return {@code true} if this executor has been shut down
*/
boolean isShutdown();

/**
* Returns {@code true} if all tasks have completed following shut down.
* Note that {@code isTerminated} is never {@code true} unless
* either {@code shutdown} or {@code shutdownNow} was called first.
*
* @return {@code true} if all tasks have completed following shut down
*/
boolean isTerminated();

/**
* Blocks until all tasks have completed execution after a shutdown
* request, or the timeout occurs, or the current thread is
* interrupted, whichever happens first.
*
* @param timeout the maximum time to wait
* @param unit the time unit of the timeout argument
* @return {@code true} if this executor terminated and
*         {@code false} if the timeout elapsed before termination
* @throws InterruptedException if interrupted while waiting
*/
boolean awaitTermination(long timeout, TimeUnit unit)
throws InterruptedException;

/**
* Submits a value-returning task for execution and returns a
* Future representing the pending results of the task. The
* Future's {@code get} method will return the task's result upon
* successful completion.
*
* <p>
* If you would like to immediately block waiting
* for a task, you can use constructions of the form
* {@code result = exec.submit(aCallable).get();}
*
* <p>Note: The {@link Executors} class includes a set of methods
* that can convert some other common closure-like objects,
* for example, {@link java.security.PrivilegedAction} to
* {@link Callable} form so they can be submitted.
*
* @param task the task to submit
* @param <T> the type of the task's result
* @return a Future representing pending completion of the task
* @throws RejectedExecutionException if the task cannot be
*         scheduled for execution
* @throws NullPointerException if the task is null
*/
<T> Future<T> submit(Callable<T> task);

/**
* Submits a Runnable task for execution and returns a Future
* representing that task. The Future's {@code get} method will
* return the given result upon successful completion.
*
* @param task the task to submit
* @param result the result to return
* @param <T> the type of the result
* @return a Future representing pending completion of the task
* @throws RejectedExecutionException if the task cannot be
*         scheduled for execution
* @throws NullPointerException if the task is null
*/
<T> Future<T> submit(Runnable task, T result);

/**
* Submits a Runnable task for execution and returns a Future
* representing that task. The Future's {@code get} method will
* return {@code null} upon <em>successful</em> completion.
*
* @param task the task to submit
* @return a Future representing pending completion of the task
* @throws RejectedExecutionException if the task cannot be
*         scheduled for execution
* @throws NullPointerException if the task is null
*/
Future<?> submit(Runnable task);

/**
* Executes the given tasks, returning a list of Futures holding
* their status and results when all complete.
* {@link Future#isDone} is {@code true} for each
* element of the returned list.
* Note that a <em>completed</em> task could have
* terminated either normally or by throwing an exception.
* The results of this method are undefined if the given
* collection is modified while this operation is in progress.
*
* @param tasks the collection of tasks
* @param <T> the type of the values returned from the tasks
* @return a list of Futures representing the tasks, in the same
*         sequential order as produced by the iterator for the
*         given task list, each of which has completed
* @throws InterruptedException if interrupted while waiting, in
*         which case unfinished tasks are cancelled
* @throws NullPointerException if tasks or any of its elements are {@code null}
* @throws RejectedExecutionException if any task cannot be
*         scheduled for execution
*/
<T> List<Future<T>> invokeAll(Collection<? extends Callable<T>> tasks)
throws InterruptedException;

/**
* Executes the given tasks, returning a list of Futures holding
* their status and results
* when all complete or the timeout expires, whichever happens first.
* {@link Future#isDone} is {@code true} for each
* element of the returned list.
* Upon return, tasks that have not completed are cancelled.
* Note that a <em>completed</em> task could have
* terminated either normally or by throwing an exception.
* The results of this method are undefined if the given
* collection is modified while this operation is in progress.
*
* @param tasks the collection of tasks
* @param timeout the maximum time to wait
* @param unit the time unit of the timeout argument
* @param <T> the type of the values returned from the tasks
* @return a list of Futures representing the tasks, in the same
*         sequential order as produced by the iterator for the
*         given task list. If the operation did not time out,
*         each task will have completed. If it did time out, some
*         of these tasks will not have completed.
* @throws InterruptedException if interrupted while waiting, in
*         which case unfinished tasks are cancelled
* @throws NullPointerException if tasks, any of its elements, or
*         unit are {@code null}
* @throws RejectedExecutionException if any task cannot be scheduled
*         for execution
*/
<T> List<Future<T>> invokeAll(Collection<? extends Callable<T>> tasks,
long timeout, TimeUnit unit)
throws InterruptedException;

/**
* Executes the given tasks, returning the result
* of one that has completed successfully (i.e., without throwing
* an exception), if any do. Upon normal or exceptional return,
* tasks that have not completed are cancelled.
* The results of this method are undefined if the given
* collection is modified while this operation is in progress.
*
* @param tasks the collection of tasks
* @param <T> the type of the values returned from the tasks
* @return the result returned by one of the tasks
* @throws InterruptedException if interrupted while waiting
* @throws NullPointerException if tasks or any element task
*         subject to execution is {@code null}
* @throws IllegalArgumentException if tasks is empty
* @throws ExecutionException if no task successfully completes
* @throws RejectedExecutionException if tasks cannot be scheduled
*         for execution
*/
<T> T invokeAny(Collection<? extends Callable<T>> tasks)
throws InterruptedException, ExecutionException;

/**
* Executes the given tasks, returning the result
* of one that has completed successfully (i.e., without throwing
* an exception), if any do before the given timeout elapses.
* Upon normal or exceptional return, tasks that have not
* completed are cancelled.
* The results of this method are undefined if the given
* collection is modified while this operation is in progress.
*
* @param tasks the collection of tasks
* @param timeout the maximum time to wait
* @param unit the time unit of the timeout argument
* @param <T> the type of the values returned from the tasks
* @return the result returned by one of the tasks
* @throws InterruptedException if interrupted while waiting
* @throws NullPointerException if tasks, or unit, or any element
*         task subject to execution is {@code null}
* @throws TimeoutException if the given timeout elapses before
*         any task successfully completes
* @throws ExecutionException if no task successfully completes
* @throws RejectedExecutionException if tasks cannot be scheduled
*         for execution
*/
<T> T invokeAny(Collection<? extends Callable<T>> tasks,
long timeout, TimeUnit unit)
throws InterruptedException, ExecutionException, TimeoutException;
}

AbstractExecutorService

对

ExecutorService

一些方法做了默认的实现，主要是submit和invoke方法。

真正的任务执行
的Executor接口

execute

方法是由子类实现，就是

ThreadPoolExecutor

，它实现了基于线程池的任务执行框架。

1.ctl

private final AtomicInteger ctl = new AtomicInteger(ctlOf(RUNNING,
0));

这个变量是整个类的核心，

AtomicInteger

保证了对这个变量的操作是原子的，通过巧妙的操作，ThreadPoolExecutor用这一个变量保存了两个内容：
所有有效线程的数量
各个线程的状态（runState）

低29位存线程数，高3位存

runState

,这样runState有5个值：
RUNNING:-536870912
SHUTDOWN:0
STOP:536870912
TIDYING:1073741824： 所有的任务都已经停止，workerCount为0，线程变成TIDYING状态会运行terminate()
TERMINATED:1610612736：terminated（）已经完成

线程池中各个状态间的转换比较复杂，主要记住下面内容就可以了：
RUNNING状态：线程池正常运行，可以接受新的任务并处理队列中的任务；
SHUTDOWN状态：不再接受新的任务，但是会执行队列中的任务；
STOP状态：不再接受新任务，不处理队列中的任务

状态转换：
1. Running ->shutdown: shutdown(),可能暗含在finalize中
2. Running /shutdown -> stop: shotdownNow
3. shutdown -> tidying: 当队列和线程池都为空
4. stop -> TIDYING: 当线程池为空
5. tidying->terminated: terminated()完成
当状态变为teminated时，线程在awaitTermination()中的等待会返回。

围绕ctl变量有一些操作，了解这些方法是看懂后面一些晦涩代码的基础：

/**
* 这个方法用于取出runState的值 因为CAPACITY值为：00011111111111111111111111111111
* ~为按位取反操作，则~CAPACITY值为：11100000000000000000000000000000
* 再同参数做&操作，就将低29位置0了，而高3位还是保持原先的值，也就是runState的值
*
* @param c
*            该参数为存储runState和workerCount的int值
* @return runState的值
*/
private static int runStateOf(int c) {
return c & ~CAPACITY;
}

/**
* 这个方法用于取出workerCount的值
* 因为CAPACITY值为：00011111111111111111111111111111，所以&操作将参数的高3位置0了
* 保留参数的低29位，也就是workerCount的值
*
* @param c
*            ctl, 存储runState和workerCount的int值
* @return workerCount的值
*/
private static int workerCountOf(int c) {
return c & CAPACITY;
}

/**
* 将runState和workerCount存到同一个int中
* “|”运算的意思是，假设rs的值是101000，wc的值是000111，则他们位或运算的值为101111
*
* @param rs
*            runState移位过后的值，负责填充返回值的高3位
* @param wc
*            workerCount移位过后的值，负责填充返回值的低29位
* @return 两者或运算过后的值
*/
private static int ctlOf(int rs, int wc) {
return rs | wc;
}

// 只有RUNNING状态会小于0
private static boolean isRunning(int c) {
return c < SHUTDOWN;
}

2.CorePoolSize

核心线程池大小，活动线程小于corePoolSize则直接创建，大于等于则先加到workQueue中，队列满了才创建新的线程。

3.KeepAliveTime

线程从队列中获取任务的超时时间，也就是说如果线程空闲超过这个时间就会终止。

4.Work

/**
* Class Worker mainly maintains interrupt control state for
* threads running tasks, along with other minor bookkeeping.
* This class opportunistically extends AbstractQueuedSynchronizer
* to simplify acquiring and releasing a lock surrounding each
* task execution.  This protects against interrupts that are
* intended to wake up a worker thread waiting for a task from
* instead interrupting a task being run.  We implement a simple
* non-reentrant mutual exclusion lock rather than use
* ReentrantLock because we do not want worker tasks to be able to
* reacquire the lock when they invoke pool control methods like
* setCorePoolSize.  Additionally, to suppress interrupts until
* the thread actually starts running tasks, we initialize lock
* state to a negative value, and clear it upon start (in
* runWorker).
*/
private final class Worker
extends AbstractQueuedSynchronizer
implements Runnable
{
/**
* This class will never be serialized, but we provide a
* serialVersionUID to suppress a javac warning.
*/
private static final long serialVersionUID = 6138294804551838833L;

/** Thread this worker is running in.  Null if factory fails. */
final Thread thread;
/** Initial task to run.  Possibly null. */
Runnable firstTask;
/** Per-thread task counter */
volatile long completedTasks;

/**
* Creates with given first task and thread from ThreadFactory.
* @param firstTask the first task (null if none)
*/
Worker(Runnable firstTask) {
setState(-1); // inhibit interrupts until runWorker
this.firstTask = firstTask;
this.thread = getThreadFactory().newThread(this);
}

/** Delegates main run loop to outer runWorker  */
public void run() {
runWorker(this);
}

// Lock methods
//
// The value 0 represents the unlocked state.
// The value 1 represents the locked state.

protected boolean isHeldExclusively() {
return getState() != 0;
}
// state只有0和1，互斥
protected boolean tryAcquire(int unused) {
if (compareAndSetState(0, 1)) {
setExclusiveOwnerThread(Thread.currentThread());
return true;// 成功获得锁

}
// 线程进入等待队列
return false;
}

protected boolean tryRelease(int unused) {
setExclusiveOwnerThread(null);
setState(0);
return true;
}

public void lock()        { acquire(1); }
public boolean tryLock()  { return tryAcquire(1); }
public void unlock()      { release(1); }
public boolean isLocked() { return isHeldExclusively(); }

void interruptIfStarted() {
Thread t;
if (getState() >= 0 && (t = thread) != null && !t.isInterrupted()) {
try {
t.interrupt();
} catch (SecurityException ignore) {
}
}
}
}

继承于AbstractQueuedSynchronizer类，任务执行时获取释放锁，这样可以防止中断，目的在于唤醒线程，而不是中断正在执行的任务。

用AQS框架实现了一个简单的非重入的互斥锁， 实现互斥锁主要目的是为了中断的时候判断线程是在空闲还是运行，可以看后面

shutdown

和

shutdownNow

方法的分析(tryAcquire和tryRelease)。

之所以不用ReentrantLock是为了避免任务执行的代码中修改线程池的变量，如

setCorePoolSize

，因为ReentrantLock是可重入的。

5.Execute

execute

方法主要三个步骤：
活动线程小于corePoolSize的时候创建新的线程；
活动线程大于corePoolSize时都是先加入到任务队列当中；
任务队列满了再去启动新的线程，如果线程数达到最大值就拒绝任务。

/**
* 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 {@code 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.
*/
int c = ctl.get();
// 活动线程数 < corePoolSize
if (workerCountOf(c) < corePoolSize) {
// 直接启动新的线程。第二个参数true:addWorker中会重新检查workerCount是否小于corePoolSize
if (addWorker(command, true))
// 添加成功返回
return;
c = ctl.get();
}

// 活动线程数 >= corePoolSize
// runState为RUNNING && 队列未满
if (isRunning(c) && workQueue.offer(command)) {
int recheck = ctl.get();
// double check
// 非RUNNING状态 则从workQueue中移除任务并拒绝
if (! isRunning(recheck) && remove(command))
reject(command);// 采用线程池指定的策略拒绝任务
// 线程池处于RUNNING状态 || 线程池处于非RUNNING状态但是任务移除失败
else if (workerCountOf(recheck) == 0)
// 这行代码是为了SHUTDOWN状态下没有活动线程了，但是队列里还有任务没执行这种特殊情况。
// 添加一个null任务是因为SHUTDOWN状态下，线程池不再接受新任务
addWorker(null, false);
// 两种情况：
// 1.非RUNNING状态拒绝新的任务
// 2.队列满了启动新的线程失败（workCount > maximumPoolSize）
}
else if (!addWorker(command, false))
reject(command);
}

其中比较难理解的应该是

addWorker(null,
false);

这一行，这要结合addWorker一起来看。 主要目的是防止HUTDOWN状态下没有活动线程了，但是队列里还有任务没执行这种特殊情况。

6.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();
int rs = runStateOf(c);//当前线程池状态

// Check if queue empty only if necessary.
// 这条语句等价：rs >= SHUTDOWN && (rs != SHUTDOWN || firstTask != null ||
// workQueue.isEmpty())
// 满足下列调价则直接返回false，线程创建失败:
// rs > SHUTDOWN:STOP || TIDYING || TERMINATED 此时不再接受新的任务，且所有任务执行结束
// rs = SHUTDOWN:firtTask != null 此时不再接受任务，但是仍然会执行队列中的任务
// rs = SHUTDOWN:firtTask == null见execute方法的addWorker(null,
// false)，任务为null && 队列为空
// 最后一种情况也就是说SHUTDONW状态下，如果队列不为空还得接着往下执行，为什么？add一个null任务目的到底是什么？
// 看execute方法只有workCount==0的时候firstTask才会为null结合这里的条件就是线程池SHUTDOWN了不再接受新任务
// 但是此时队列不为空，那么还得创建线程把任务给执行完才行。
if (rs >= SHUTDOWN &&
! (rs == SHUTDOWN &&
firstTask == null &&
! workQueue.isEmpty()))
return false;
// 走到这的情形：
// 1.线程池状态为RUNNING
// 2.SHUTDOWN状态，但队列中还有任务需要执行
for (;;) {
int wc = workerCountOf(c);
if (wc >= CAPACITY ||
wc >= (core ? corePoolSize : maximumPoolSize))
return false;
if (compareAndIncrementWorkerCount(c))// 原子操作递增workCount
break retry;// 操作成功跳出的重试的循环
c = ctl.get();  // Re-read ctl
if (runStateOf(c) != rs)// 如果线程池的状态发生变化则重试
continue retry;
// else CAS failed due to workerCount change; retry inner loop
}
}

// wokerCount递增成功

boolean workerStarted = false;
boolean workerAdded = false;
Worker w = null;
try {
w = new Worker(firstTask);
final Thread t = w.thread;
if (t != null) {
final ReentrantLock mainLock = this.mainLock;
// 并发的访问线程池workers对象必须加锁
mainLock.lock();
try {
// Recheck while holding lock.
// Back out on ThreadFactory failure or if
// shut down before lock acquired.
int rs = runStateOf(ctl.get());

// RUNNING状态 || SHUTDONW状态下清理队列中剩余的任务
if (rs < SHUTDOWN ||
(rs == SHUTDOWN && firstTask == null)) {
if (t.isAlive()) // precheck that t is startable
throw new IllegalThreadStateException();
// 将新启动的线程添加到线程池中
workers.add(w);
// 更新largestPoolSize
int s = workers.size();
if (s > largestPoolSize)
largestPoolSize = s;
workerAdded = true;
}
} finally {
mainLock.unlock();
}
// 启动新添加的线程，这个线程首先执行firstTask，然后不停的从队列中取任务执行
// 当等待keepAlieTime还没有任务执行则该线程结束。见runWoker和getTask方法的代码。
if (workerAdded) {
t.start();//最终执行的是ThreadPoolExecutor的runWoker方法
workerStarted = true;
}
}
} finally {
// 线程启动失败，则从wokers中移除w并递减wokerCount
if (! workerStarted)
// 递减wokerCount会触发tryTerminate方法
addWorkerFailed(w);
}
return workerStarted;
}

7. runWorker

任务添加成功后实际执行的是

runWorker

这个方法，这个方法非常重要，简单来说它做的就是：
第一次启动会执行初始化传进来的任务firstTask；
然后会从workQueue中取任务执行，如果队列为空则等待keepAliveTime这么长时间。

/**
* 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
*/
final void runWorker(Worker w) {
Thread wt = Thread.currentThread();
Runnable task = w.firstTask;
w.firstTask = null;
// Worker的构造函数中抑制了线程中断setState(-1)，所以这里需要unlock从而允许中断
w.unlock(); // allow interrupts
// 用于标识是否异常终止，finally中processWorkerExit的方法会有不同逻辑
// 为true的情况：1.执行任务抛出异常；2.被中断。
boolean completedAbruptly = true;
try {
// 如果getTask返回null那么getTask中会将workerCount递减，如果异常了这个递减操作会在processWorkerExit中处理
while (task != null || (task = getTask()) != null) {
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
if ((runStateAtLeast(ctl.get(), STOP) ||
(Thread.interrupted() &&
runStateAtLeast(ctl.get(), STOP))) &&
!wt.isInterrupted())
wt.interrupt();
try {
// 任务执行前可以插入一些处理，子类重载该方法
beforeExecute(wt, task);
Throwable thrown = null;
try {
task.run();//执行用户任务
} catch (RuntimeException x) {
thrown = x; throw x;
} catch (Error x) {
thrown = x; throw x;
} catch (Throwable x) {
thrown = x; throw new Error(x);
} finally {
// 和beforeExecute一样，留给子类去重载
afterExecute(task, thrown);
}
} finally {
task = null;
w.completedTasks++;
w.unlock();
}
}
completedAbruptly = false;
} finally {
// 结束线程的一些清理工作
processWorkerExit(w, completedAbruptly);
}
}

8.getTask

/**
* Performs blocking or timed wait for a task, depending on
* current configuration settings, or returns null if this worker
* must exit because of any of:
* 1. There are more than maximumPoolSize workers (due to
*    a call to setMaximumPoolSize).
* 2. The pool is stopped.
* 3. The pool is shutdown and the queue is empty.
* 4. This worker timed out waiting for a task, and timed-out
*    workers are subject to termination (that is,
*    {@code allowCoreThreadTimeOut || workerCount > corePoolSize})
*    both before and after the timed wait, and if the queue is
*    non-empty, this worker is not the last thread in the pool.
*
* @return task, or null if the worker must exit, in which case
*         workerCount is decremented
*/
private Runnable getTask() {
boolean timedOut = false; // Did the last poll() time out?

for (;;) {
int c = ctl.get();
int rs = runStateOf(c);

// Check if queue empty only if necessary.
// 1.rs > SHUTDOWN 所以rs至少等于STOP,这时不再处理队列中的任务
// 2.rs = SHUTDOWN 所以rs>=STOP肯定不成立，这时还需要处理队列中的任务除非队列为空
// 这两种情况都会返回null让runWoker退出while循环也就是当前线程结束了，所以必须要decrement
// wokerCount
if (rs >= SHUTDOWN && (rs >= STOP || workQueue.isEmpty())) {
// 递减workerCount值
decrementWorkerCount();
return null;
}

int wc = workerCountOf(c);

// Are workers subject to culling?

// 1.core thread允许被超时，那么超过corePoolSize的的线程必定有超时
// 2.allowCoreThreadTimeOut == false && wc >
// corePoolSize时，一般都是这种情况，core thread即使空闲也不会被回收，只要超过的线程才会
boolean timed = allowCoreThreadTimeOut || wc > corePoolSize;

// 从addWorker可以看到一般wc不会大于maximumPoolSize，所以更关心后面半句的情形：
// 1. timedOut == false 第一次执行循环， 从队列中取出任务不为null方法返回 或者
// poll出异常了重试
// 2.timeOut == true && timed ==
// false:看后面的代码workerQueue.poll超时时timeOut才为true，
// 并且timed要为false，这两个条件相悖不可能同时成立（既然有超时那么timed肯定为true）
// 所以超时不会继续执行而是return null结束线程。（重点：线程是如何超时的？？？）
if ((wc > maximumPoolSize || (timed && timedOut))
&& (wc > 1 || workQueue.isEmpty())) {
// workerCount递减，结束当前thread
if (compareAndDecrementWorkerCount(c))
return null;
continue;
}

try {
// 1.以指定的超时时间从队列中取任务
// 2.core thread没有超时
Runnable r = timed ?
workQueue.poll(keepAliveTime, TimeUnit.NANOSECONDS) :
workQueue.take();
if (r != null)
return r;
timedOut = true;// 超时
} catch (InterruptedException retry) {
timedOut = false;// 线程被中断重试
}
}
}

9.ProcessWorkerExit
线程退出会执行这个方法做一些清理工作。

/**
* 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
*/
private void processWorkerExit(Worker w, boolean completedAbruptly) {
// 正常的话再runWorker的getTask方法workerCount已经被减一了
if (completedAbruptly) // If abrupt, then workerCount wasn't adjusted
decrementWorkerCount();

final ReentrantLock mainLock = this.mainLock;
mainLock.lock();
try {
// 累加线程的completedTasks
completedTaskCount += w.completedTasks;
// 从线程池中移除超时或者出现异常的线程
workers.remove(w);
} finally {
mainLock.unlock();
}

// 尝试停止线程池
tryTerminate();

int c = ctl.get();
// runState为RUNNING或SHUTDOWN
if (runStateLessThan(c, STOP)) {
// 线程不是异常结束
if (!completedAbruptly) {
// 线程池最小空闲数，允许core thread超时就是0，否则就是corePoolSize
int min = allowCoreThreadTimeOut ? 0 : corePoolSize;
// 如果min == 0但是队列不为空要保证有1个线程来执行队列中的任务
if (min == 0 && ! workQueue.isEmpty())
min = 1;
// 线程池还不为空那就不用担心了
if (workerCountOf(c) >= min)
return; // replacement not needed
}
// 1.线程异常退出
// 2.线程池为空，但是队列中还有任务没执行，看addWoker方法对这种情况的处理
addWorker(null, false);
}
}

10. TryTerminate

processWorkerExit方法中会尝试调用tryTerminate来终止线程池。这个方法在任何可能导致线程池终止的动作后执行：比如减少wokerCount或SHUTDOWN状态下从队列中移除任务。

/**
* 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.
*/
final void tryTerminate() {
for (;;) {
int c = ctl.get();
// 以下状态直接返回：
// 1.线程池还处于RUNNING状态
// 2.SHUTDOWN状态但是任务队列非空
// 3.runState >= TIDYING 线程池已经停止了或在停止了
if (isRunning(c) ||
runStateAtLeast(c, TIDYING) ||
(runStateOf(c) == SHUTDOWN && ! workQueue.isEmpty()))
return;
// 只能是以下情形会继续下面的逻辑：结束线程池。
// 1.SHUTDOWN状态，这时不再接受新任务而且任务队列也空了
// 2.STOP状态，当调用了shutdownNow方法

// workerCount不为0则还不能停止线程池,而且这时线程都处于空闲等待的状态
// 需要中断让线程“醒”过来，醒过来的线程才能继续处理shutdown的信号。
if (workerCountOf(c) != 0) { // Eligible to terminate
// runWoker方法中w.unlock就是为了可以被中断,getTask方法也处理了中断。
// ONLY_ONE:这里只需要中断1个线程去处理shutdown信号就可以了。
interruptIdleWorkers(ONLY_ONE);
return;
}

final ReentrantLock mainLock = this.mainLock;
mainLock.lock();
try {
// 进入TIDYING状态
if (ctl.compareAndSet(c, ctlOf(TIDYING, 0))) {
try {
// 子类重载：一些资源清理工作
terminated();
} finally {
// TERMINATED状态
ctl.set(ctlOf(TERMINATED, 0));
// 继续awaitTermination
termination.signalAll();
}
return;
}
} finally {
mainLock.unlock();
}
// else retry on failed CAS
}
}

11.ShutDown 和ShutDownNow

shutdown这个方法会将runState置为

SHUTDOWN

，会终止所有空闲的线程。

/**
* Initiates an orderly shutdown in which previously submitted
* tasks are executed, but no new tasks will be accepted.
* Invocation has no additional effect if already shut down.
*
* <p>This method does not wait for previously submitted tasks to
* complete execution.  Use {@link #awaitTermination awaitTermination}
* to do that.
*
* @throws SecurityException {@inheritDoc}
*/
public void shutdown() {
final ReentrantLock mainLock = this.mainLock;
mainLock.lock();
try {
checkShutdownAccess();
// 线程池状态设为SHUTDOWN，如果已经至少是这个状态那么则直接返回
advanceRunState(SHUTDOWN);
// 注意这里是中断所有空闲的线程：runWorker中等待的线程被中断 → 进入processWorkerExit →
// tryTerminate方法中会保证队列中剩余的任务得到执行。
interruptIdleWorkers();
onShutdown(); // hook for ScheduledThreadPoolExecutor
} finally {
mainLock.unlock();
}
tryTerminate();
}

shutdownNow方法将runState置为STOP。和shutdown方法的区别，这个方法会终止所有的线程。

/**
* Attempts to stop all actively executing tasks, halts the
* processing of waiting tasks, and returns a list of the tasks
* that were awaiting execution. These tasks are drained (removed)
* from the task queue upon return from this method.
*
* <p>This method does not wait for actively executing tasks to
* terminate.  Use {@link #awaitTermination awaitTermination} to
* do that.
*
* <p>There are no guarantees beyond best-effort attempts to stop
* processing actively executing tasks.  This implementation
* cancels tasks via {@link Thread#interrupt}, so any task that
* fails to respond to interrupts may never terminate.
*
* @throws SecurityException {@inheritDoc}
*/
public List<Runnable> shutdownNow() {
List<Runnable> tasks;
final ReentrantLock mainLock = this.mainLock;
mainLock.lock();
try {
checkShutdownAccess();
// STOP状态：不再接受新任务且不再执行队列中的任务。
advanceRunState(STOP);
// 中断所有线程
interruptWorkers();
// 返回队列中还没有被执行的任务。
tasks = drainQueue();
} finally {
mainLock.unlock();
}
tryTerminate();
return tasks;
}

public boolean isShutdown() {
return ! isRunning(ctl.get());
}

主要区别在于shutdown调用的是

interruptIdleWorkers

这个方法，而shutdownNow实际调用的是Worker类的

interruptIfStarted

方法：

/**
* Interrupts threads that might be waiting for tasks (as
* indicated by not being locked) so they can check for
* termination or configuration changes. Ignores
* SecurityExceptions (in which case some threads may remain
* uninterrupted).
*
* @param onlyOne If true, interrupt at most one worker. This is
* called only from tryTerminate when termination is otherwise
* enabled but there are still other workers.  In this case, at
* most one waiting worker is interrupted to propagate shutdown
* signals in case all threads are currently waiting.
* Interrupting any arbitrary thread ensures that newly arriving
* workers since shutdown began will also eventually exit.
* To guarantee eventual termination, it suffices to always
* interrupt only one idle worker, but shutdown() interrupts all
* idle workers so that redundant workers exit promptly, not
* waiting for a straggler task to finish.
*/
private void interruptIdleWorkers(boolean onlyOne) {
final ReentrantLock mainLock = this.mainLock;
mainLock.lock();
try {
for (Worker w : workers) {
Thread t = w.thread;
// w.tryLock能获取到锁，说明该线程没有在运行，因为runWorker中执行任务会先lock，
// 因此保证了中断的肯定是空闲的线程。
if (!t.isInterrupted() && w.tryLock()) {
try {
t.interrupt();
} catch (SecurityException ignore) {
} finally {
w.unlock();
}
}
if (onlyOne)
break;
}
} finally {
mainLock.unlock();
}
}

void interruptIfStarted() {
Thread t;
// 初始化时state == -1
if (getState() >= 0 && (t = thread) != null && !t.isInterrupted()) {
try {
t.interrupt();
} catch (SecurityException ignore) {
}
}
}

这就是前面提到的Woker类实现AQS的主要作用。