ThreadPoolExecutor的部分源码分析

从execute开始看起

/**
* 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();
if (workerCountOf(c) < corePoolSize) {//如果线程池里线程的数目小于corePoolSize，则增加新的线程，并在该线程中执行command
if (addWorker(command, true))
return;
c = ctl.get();
}
if (isRunning(c) && workQueue.offer(command)) {//不满足上面的if判断，加入workQueue，等待在被已有的线程池执行
int recheck = ctl.get();
if (! isRunning(recheck) && remove(command))//recheck状态，不是running的话移除刚加入队尾的command
reject(command);
else if (workerCountOf(recheck) == 0)//没有线程则加一个线程
addWorker(null, false);
}
else if (!addWorker(command, false))
reject(command);
}

接着看addWorker函数，增加WorkerCount的部分使用了CAS无锁编程。

使用lock实现线程同步有很多缺点：
* 产生竞争时，线程被阻塞等待，无法做到线程实时响应。
* dead lock。
* live lock。
* 优先级翻转。
* 使用不当，造成性能下降。
 
如果在不使用 lock 的情况下，实现变量同步，那就会避免很多问题。虽然目前来看，无锁编程并不能替代 lock。

/**
* 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) {
// 下面是一段CAS无锁编程，在不使用 lock 的情况下，实现变量同步
// ctl中pack了两个变量：
// 1、workerCount, indicating the effective number of threads
// 2、runState,    indicating whether running, shutting down etc
// 外层循环用来判断runState有没有变化，内层循环用来判断workerCount有没有变化
retry:
for (;;) {
int c = ctl.get();
int rs = runStateOf(c);

// Check if queue empty only if necessary.
if (rs >= SHUTDOWN &&
! (rs == SHUTDOWN &&
firstTask == null &&
! workQueue.isEmpty()))
return false;

for (;;) {
int wc = workerCountOf(c);
if (wc >= CAPACITY ||
wc >= (core ? corePoolSize : maximumPoolSize))
return false;
if (compareAndIncrementWorkerCount(c))
break retry;

// if (compareAndIncrementWorkerCount(c))判断失败，
// ctrl在上次读出和试图加1期间发生了改变，证明有别的线程修改了ctrl，于是重新读ctl，重试加1
c = ctl.get();  // Re-read ctl
if (runStateOf(c) != rs)
continue retry;
// else CAS failed due to workerCount change; retry inner loop (rs没变，只重试内循环)
}
}

boolean workerStarted = false;
boolean workerAdded = false;
Worker w = null;
try {
w = new Worker(firstTask);//以firstTask作为第一个运行的任务，开启一条新线程
final Thread t = w.thread;
if (t != null) {
final ReentrantLock mainLock = this.mainLock;
mainLock.lock();
try {
// Recheck while holding lock.
// Back out on ThreadFactory failure or if
// shut down before lock acquired.
int rs = runStateOf(ctl.get());

if (rs < SHUTDOWN ||
(rs == SHUTDOWN && firstTask == null)) {
if (t.isAlive()) // precheck that t is startable
throw new IllegalThreadStateException();

//新线程加入线程池，workers是一个HashSet，保存了线程池的所有线程，并且只能在mainLock的保护下访问
workers.add(w);
int s = workers.size();
if (s > largestPoolSize)
largestPoolSize = s;
workerAdded = true;
}
} finally {
mainLock.unlock();
}
if (workerAdded) {
t.start();//Worker中的thread start
workerStarted = true;
}
}
} finally {
if (! workerStarted)
addWorkerFailed(w);
}
return workerStarted;
}

/**
* Attempts to CAS-increment the workerCount field of ctl.
*/
private boolean compareAndIncrementWorkerCount(int expect) {
return ctl.compareAndSet(expect, expect + 1);
}

/**
* Set containing all worker threads in pool. Accessed only when
* holding mainLock.
*/
private final HashSet<Worker> workers = new HashSet<Worker>();

那等待队列中的Runnable什么时候才执行呢？答案在Worker中。Worker也是一个Runnable，并在run方法中调用了外部类的runWorker(this),把自己作为参数传进去

/**
* 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;
}

protected boolean tryAcquire(int unused) {
if (compareAndSetState(0, 1)) {
setExclusiveOwnerThread(Thread.currentThread());
return true;
}
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) {
}
}
}
}

/**
* 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;
w.unlock(); // allow interrupts
boolean completedAbruptly = true;
try {
// 下面的循环不断执行task.run()
// 如果firstTask非空，这是第一个执行的task，第一次不用getTask()
// 后面就通过getTask()获得新的task运行，直到getTask()为空，或者执行过程中有异常
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 {
beforeExecute(wt, task);
Throwable thrown = null;
try {
task.run();
} catch (RuntimeException x) {
thrown = x; throw x;
} catch (Error x) {
thrown = x; throw x;
} catch (Throwable x) {
thrown = x; throw new Error(x);
} finally {
afterExecute(task, thrown);
}
} finally {
task = null;
w.completedTasks++;
w.unlock();
}
}
completedAbruptly = false;
} finally {
processWorkerExit(w, completedAbruptly);
}
}

getTask()的核心就是从等待队列中取出Runnable，让线程池中的线程执行

/**
* 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.
if (rs >= SHUTDOWN && (rs >= STOP || workQueue.isEmpty())) {//英文注释中的2、3场景
decrementWorkerCount();
return null;//这种情况下worker必须exit，workerCount也减一
}

int wc = workerCountOf(c);

// Are workers subject to culling?
boolean timed = allowCoreThreadTimeOut || wc > corePoolSize;

if ((wc > maximumPoolSize || (timed && timedOut))
&& (wc > 1 || workQueue.isEmpty())) {//英文注释中的1、4场景
if (compareAndDecrementWorkerCount(c))
return null;
continue;
}

try {
//从队列中取出等待的Runnable
Runnable r = timed ?
workQueue.poll(keepAliveTime, TimeUnit.NANOSECONDS) :
workQueue.take();
if (r != null)
return r;
timedOut = true;
} catch (InterruptedException retry) {
timedOut = false;
}
}
}