Android Looper与Message

Android的Handler机制是一个非常强大的消息的机制系统，Handler机制的使用在Android整个系统中随处可见。

Handler作为消息中转器和处理器，是用户进行消息处理的最直接接口，而消息的队列处理和按序分发，即Handler机制的背后支持，则是由Looper和MessageQueue来进行处理。

这里不对Handler做相关介绍，重点是Looper和MessageQueue怎么来配合完成的。

从源码角度看从 handler.sendMessage 到 handleMessage 的整个过程。

以Handler作为入口：

sendMessage：

public final boolean sendMessage(Message msg)
{
    return sendMessageDelayed(msg, 0);
}

public final boolean sendMessageDelayed(Message msg, long delayMillis)
{
    if (delayMillis < 0) {
        delayMillis = 0;
    }
    return sendMessageAtTime(msg, SystemClock.uptimeMillis() + delayMillis);
}

public boolean sendMessageAtTime(Message msg, long uptimeMillis) {
    MessageQueue queue = mQueue;
    if (queue == null) {
        RuntimeException e = new RuntimeException(
                this + " sendMessageAtTime() called with no mQueue");
        Log.w("Looper", e.getMessage(), e);
        return false;
    }
    //这里开始进入MessageQueue逻辑
    return enqueueMessage(queue, msg, uptimeMillis);
}

MessageQueue

调用MessageQueue的 enqueueMessage

/*
* 1. 非法情况判别
* 2. 当队列为空，msg入队，唤醒epoll_wait
* 3. 队列不为空，链表末尾，加入msg
* */
boolean enqueueMessage(Message msg, long when) {
    if (msg.target == null) {
        throw new IllegalArgumentException("Message must have a target.");
    }
    if (msg.isInUse()) {
        throw new IllegalStateException(msg + " This message is already in use.");
    }

    synchronized (this) {
        if (mQuitting) {
            IllegalStateException e = new IllegalStateException(
                    msg.target + " sending message to a Handler on a dead thread");
            Log.w("MessageQueue", e.getMessage(), e);
            msg.recycle();
            return false;
        }

        msg.markInUse();
        msg.when = when;
        Message p = mMessages;
        boolean needWake;
        if (p == null || when == 0 || when < p.when) {
            //当队列还没有任何消息的时候
            //将message入队,这里是链表的形式, 并没有队列或者数组来进行维护
            // New head, wake up the event queue if blocked.
            msg.next = p;
            mMessages = msg;
            //当队列为空,则looper会处于block状态
            needWake = mBlocked;
        } else {
            //队列本来已经有数据
            // Inserted within the middle of the queue.  Usually we don't have to wake
            // up the event queue unless there is a barrier at the head of the queue
            // and the message is the earliest asynchronous message in the queue.
            //是否需要唤醒当前的等待
            needWake = mBlocked && p.target == null && msg.isAsynchronous();
            Message prev;
            //遍历到队列末尾
            for (;;) {
                prev = p;
                p = p.next;
                if (p == null || when < p.when) {
                    break;
                }
                if (needWake && p.isAsynchronous()) {
                    needWake = false;
                }
            }
            //将msg加入到队列末尾
            msg.next = p; // invariant: p == prev.next
            prev.next = msg;
        }

        // We can assume mPtr != 0 because mQuitting is false.
        if (needWake) {
            //这里是唤醒底层的epoll_wait，此时可能looper正处于空队列等待状态，有新加入的message后需要唤醒
            nativeWake(mPtr);
        }
    }
    return true;
}

这里有几个重要的变量：

// True if the message queue can be quit.
//是否可以被退出
private final boolean mQuitAllowed;

//NativeMessageQueue对象的地址,MessageQueue的等待和唤醒机制是在JNI下执行的
@SuppressWarnings("unused")
private long mPtr; // used by native code

//Message链表的头
Message mMessages;
//IdleHandler集合,用来在队列执行到空的时候进行回调
private final ArrayList<IdleHandler> mIdleHandlers = new ArrayList<IdleHandler>();
//mIdleHandlers的数组形式,在调用的时候会对mIdleHandlers进行一份拷贝
private IdleHandler[] mPendingIdleHandlers;
//是否MessageQueue正在退出(退出操作使用Looper.quit进行触发)
private boolean mQuitting;

// Indicates whether next() is blocked waiting in pollOnce() with a non-zero timeout.
//标记当前Lopper是否处于block状态
private boolean mBlocked;

// The next barrier token.
// Barriers are indicated by messages with a null target whose arg1 field carries the token.
private int mNextBarrierToken;

private native static long nativeInit();
private native static void nativeDestroy(long ptr);
//nativePollOnce主要触发等待机制
private native static void nativePollOnce(long ptr, int timeoutMillis);
//nativeWake在合适是时机下唤醒epoll_wait等待
private native static void nativeWake(long ptr);
private native static boolean nativeIsIdling(long ptr);

入队之后, Looper会被唤醒, 并从MessageQueue中依次取出message，直到MessageQueue为空（所有的消息都被处理完了）；

Looper

Looper对象是每一个线程有一个，这个是一一对应的关系，每一个Looper会有一个MessageQueue， 同样是一一对应关系。

Looper.prepare

public static void prepare() {
    prepare(true);
}

//quitAllowed对应MessageQueue中的mQuitAllowed, 在创建Looper的时候就已经指定, 默认可以被取消,否则会抛出异常
//这里没有提供对应的接口,所以所有的Looper理论上都是可以被取消的

private static void prepare(boolean quitAllowed) {
    if (sThreadLocal.get() != null) {
        throw new RuntimeException("Only one Looper may be created per thread");
    }
    //用ThreadLocal为当前线程唯一保存一份Looper对象
    sThreadLocal.set(new Looper(quitAllowed));
}

每个looper对应一个MessageQueue:

private Looper(boolean quitAllowed) {
    mQueue = new MessageQueue(quitAllowed);
    mThread = Thread.currentThread();
}

Looper.loop()

/*
* 1. 从MessageQueue中取出下一个待处理的Message对象；
* 2. 调用对应的Handler的dispatchMessage分发消息
* */
public static void loop() {
    final Looper me = myLooper();
    if (me == null) {
        throw new RuntimeException("No Looper; Looper.prepare() wasn't called on this thread.");
    }
    final MessageQueue queue = me.mQueue;

    // Make sure the identity of this thread is that of the local process,
    // and keep track of what that identity token actually is.
    Binder.clearCallingIdentity();
    final long ident = Binder.clearCallingIdentity();

    for (;;) {
        //取得MessageQueue中的下一个待处理的Message
        Message msg = queue.next(); // might block
        if (msg == null) {
            // No message indicates that the message queue is quitting.
            return;
        }

        // This must be in a local variable, in case a UI event sets the logger
        Printer logging = me.mLogging;
        if (logging != null) {
            logging.println(">>>>> Dispatching to " + msg.target + " " +
                    msg.callback + ": " + msg.what);
        }

        //分发消息,target是msg中绑定的Handler,这里就会发送msg对象到handleMessage中进行处理.
        msg.target.dispatchMessage(msg);

        if (logging != null) {
            logging.println("<<<<< Finished to " + msg.target + " " + msg.callback);
        }

        // Make sure that during the course of dispatching the
        // identity of the thread wasn't corrupted.
        final long newIdent = Binder.clearCallingIdentity();
        if (ident != newIdent) {
            Log.wtf(TAG, "Thread identity changed from 0x"
                    + Long.toHexString(ident) + " to 0x"
                    + Long.toHexString(newIdent) + " while dispatching to "
                    + msg.target.getClass().getName() + " "
                    + msg.callback + " what=" + msg.what);
        }

        msg.recycleUnchecked();
    }
}

Handler.dispatchMessage:

public void dispatchMessage(Message msg) {
    if (msg.callback != null) {
        //首先优先调用Message的callback（Runnable）的run方法
        handleCallback(msg);
    } else {
        if (mCallback != null) {
            //如果essage的callback（Runnable）不存在,其次调用Handler的CallBack对象的handleMessage
            if (mCallback.handleMessage(msg)) {
                return;
            }
        }
        
        //最后才会调用Handler自己的handleMessage方法
        handleMessage(msg);
    }
}

最终会走到我们的handleMessage中, 然后根据情况进行处理.

然而这里的重点,其实是Looper.loop中的queue.next()方法，注意这里的注释（该方法可能会阻塞）：

Message msg = queue.next(); // might block

MessageQueue.next()

/*
* 1. 循环从队列中取Message;
* 2. 判断该Message是否是一个Barrier, 如果是,则不执行后面所有的同步的message,异步Message不受影响, 默认的message都是同步的;
* 3. 如果没有Barrier, 则依次从Message链表中取出前面的Message;
* 4. 判断当前的MessageQueue是否有设置IdleHandler,在队列为空的时候去回调他的方法queueIdle.
* */
Message next() {
    // Return here if the message loop has already quit and been disposed.
    // This can happen if the application tries to restart a looper after quit
    // which is not supported.
    final long ptr = mPtr;
    if (ptr == 0) {
        return null;
    }

    //标记IdleHandler的数量
    int pendingIdleHandlerCount = -1; // -1 only during first iteration
    //下次epoll_wait的超时时间, 0会立刻返回, -1 则会永远等待, >0即设置的超时等待时间
    int nextPollTimeoutMillis = 0;
    for (;;) {
        if (nextPollTimeoutMillis != 0) {
            Binder.flushPendingCommands();
        }

        //触发epoll_wait机制
        nativePollOnce(ptr, nextPollTimeoutMillis);

        synchronized (this) {
            // Try to retrieve the next message.  Return if found.
            final long now = SystemClock.uptimeMillis();
            //从队列中取出message
            Message prevMsg = null;
            Message msg = mMessages;
            //判断是否是一个barrier[MessageQueue 的Barrier后面会说到]
            if (msg != null && msg.target == null) {
                // Stalled by a barrier.  Find the next asynchronous message in the queue.
                //这里查找被Barrier绊住之后的所有非异步消息, 异步消息不会受到barrier的影响.
                //同时这里会把msg的指针移到最后(null), 目的是让barrier之后的所有同步(默认为同步)消息都没办法执行.
                do {
                    prevMsg = msg;
                    msg = msg.next;
                } while (msg != null && !msg.isAsynchronous());
            }
            //如果有barrier, 这里不会走
            if (msg != null) {
                if (now < msg.when) {
                    // Next message is not ready.  Set a timeout to wake up when it is ready.
                    nextPollTimeoutMillis = (int) Math.min(msg.when - now, Integer.MAX_VALUE);
                } else {
                    // Got a message.
                    //从链表中拿出一个msg
                    mBlocked = false;
                    if (prevMsg != null) {
                        prevMsg.next = msg.next;
                    } else {
                        mMessages = msg.next;
                    }
                    //将message从链表中剥离
                    msg.next = null;
                    if (false) Log.v("MessageQueue", "Returning message: " + msg);
                    return msg;
                }
            } else {
                // No more messages.
                //epoll_wait会一直等待
                nextPollTimeoutMillis = -1;
            }

            // Process the quit message now that all pending messages have been handled.
            if (mQuitting) {
                dispose();
                return null;
            }

            // If first time idle, then get the number of idlers to run.
            // Idle handles only run if the queue is empty or if the first message
            // in the queue (possibly a barrier) is due to be handled in the future.
            if (pendingIdleHandlerCount < 0
                    && (mMessages == null || now < mMessages.when)) {
                pendingIdleHandlerCount = mIdleHandlers.size();
            }
            if (pendingIdleHandlerCount <= 0) {
                // No idle handlers to run.  Loop and wait some more.
                mBlocked = true;
                continue;
            }

            //拿到所有IdleHandler拷贝的数组形式
            if (mPendingIdleHandlers == null) {
                mPendingIdleHandlers = new IdleHandler[Math.max(pendingIdleHandlerCount, 4)];
            }
            mPendingIdleHandlers = mIdleHandlers.toArray(mPendingIdleHandlers);
        }

        // Run the idle handlers.
        // We only ever reach this code block during the first iteration.
        for (int i = 0; i < pendingIdleHandlerCount; i++) {
            final IdleHandler idler = mPendingIdleHandlers[i];
            mPendingIdleHandlers[i] = null; // release the reference to the handler

            boolean keep = false;
            try {
                // 当队列为空的时候,回调queueIdle, 返回值决定该IdleHandler是在执行之后被保留;
                // 注意: 不保留只会在MessageQueue首次为空的时候被调用, 保留则每次为空都会被调用
                // 如果当前一直为空而没有任何消息,则在保留的情况下,该方法会一直被循环回调,这时候epoll_wait会直接返回而不会等待.
                keep = idler.queueIdle();
            } catch (Throwable t) {
                Log.wtf("MessageQueue", "IdleHandler threw exception", t);
            }

            //如果不保留会从集合中移除该IdleHandler.
            if (!keep) {
                synchronized (this) {
                    mIdleHandlers.remove(idler);
                }
            }
        }

        // Reset the idle handler count to 0 so we do not run them again.
        pendingIdleHandlerCount = 0;

        // While calling an idle handler, a new message could have been delivered
        // so go back and look again for a pending message without waiting.
        //回调IdleHandler也存在有新的message消息被发送的可能性,所以这里不会阻塞.
        nextPollTimeoutMillis = 0;
    }
}

    nativePollOnce

core/jni/android_os_MessageQueue.cpp

tatic JNINativeMethod gMessageQueueMethods[] = {
    /* name, signature, funcPtr */
    { "nativeInit", "()J", (void*)android_os_MessageQueue_nativeInit },
    { "nativeDestroy", "(J)V", (void*)android_os_MessageQueue_nativeDestroy },
    { "nativePollOnce", "(JI)V", (void*)android_os_MessageQueue_nativePollOnce },
    { "nativeWake", "(J)V", (void*)android_os_MessageQueue_nativeWake },
    { "nativeIsIdling", "(J)Z", (void*)android_os_MessageQueue_nativeIsIdling }
};

对应的NativeMessageQueue的pollOnce:

static void android_os_MessageQueue_nativePollOnce(JNIEnv* env, jclass clazz,
        jlong ptr, jint timeoutMillis) {
    NativeMessageQueue* nativeMessageQueue = reinterpret_cast<NativeMessageQueue*>(ptr);
    nativeMessageQueue->pollOnce(env, timeoutMillis);
}

NativeMessageQueue的指针对象保存在MessageQueue的Java文件里,前面提到过:

//NativeMessageQueue对象的地址,MessageQueue的等待和唤醒机制是在JNI下执行的
@SuppressWarnings("unused")
private long mPtr; // used by native code

void NativeMessageQueue::pollOnce(JNIEnv* env, int timeoutMillis) {
    mInCallback = true;
    mLooper->pollOnce(timeoutMillis);
    mInCallback = false;
    if (mExceptionObj) {
        env->Throw(mExceptionObj);
        env->DeleteLocalRef(mExceptionObj);
        mExceptionObj = NULL;
    }
}

调用到了Looper的pollOnce:

/system/core/libutils/Looper.cpp

int Looper::pollOnce(int timeoutMillis, int* outFd, int* outEvents, void** outData) {
   ......

        result = pollInner(timeoutMillis);
    }
}

int Looper::pollInner(int timeoutMillis) {
#if DEBUG_POLL_AND_WAKE
    ALOGD("%p ~ pollOnce - waiting: timeoutMillis=%d", this, timeoutMillis);
#endif

    // Adjust the timeout based on when the next message is due.
    if (timeoutMillis != 0 && mNextMessageUptime != LLONG_MAX) {
        nsecs_t now = systemTime(SYSTEM_TIME_MONOTONIC);
        int messageTimeoutMillis = toMillisecondTimeoutDelay(now, mNextMessageUptime);
        if (messageTimeoutMillis >= 0
                && (timeoutMillis < 0 || messageTimeoutMillis < timeoutMillis)) {
            timeoutMillis = messageTimeoutMillis;
        }
#if DEBUG_POLL_AND_WAKE
        ALOGD("%p ~ pollOnce - next message in %" PRId64 "ns, adjusted timeout: timeoutMillis=%d",
                this, mNextMessageUptime - now, timeoutMillis);
#endif
    }

    // Poll.
    int result = POLL_WAKE;
    mResponses.clear();
    mResponseIndex = 0;

    // We are about to idle.
    mPolling = true;

    struct epoll_event eventItems[EPOLL_MAX_EVENTS];
    //整理调用epoll_wait进行等待, eventCount = 0的话表示已经超时.
    //timeoutMillis 是从java层传递下来的nextPollTimeoutMillis.
    int eventCount = epoll_wait(mEpollFd, eventItems, EPOLL_MAX_EVENTS, timeoutMillis);

    // No longer idling.
    mPolling = false;

    // Acquire lock.
    mLock.lock();

    // Rebuild epoll set if needed.
    if (mEpollRebuildRequired) {
        mEpollRebuildRequired = false;
        rebuildEpollLocked();
        goto Done;
    }

    // Check for poll error.
    if (eventCount < 0) {
        if (errno == EINTR) {
            goto Done;
        }
        ALOGW("Poll failed with an unexpected error: %s", strerror(errno));
        result = POLL_ERROR;
        goto Done;
    }

    // Check for poll timeout.
    if (eventCount == 0) {
#if DEBUG_POLL_AND_WAKE
        ALOGD("%p ~ pollOnce - timeout", this);
#endif
        result = POLL_TIMEOUT;
        goto Done;
    }

    // Handle all events.
#if DEBUG_POLL_AND_WAKE
    ALOGD("%p ~ pollOnce - handling events from %d fds", this, eventCount);
#endif

    for (int i = 0; i < eventCount; i++) {
        int fd = eventItems[i].data.fd;
        uint32_t epollEvents = eventItems[i].events;
        if (fd == mWakeEventFd) {
            if (epollEvents & EPOLLIN) {
                awoken();
            } else {
                ALOGW("Ignoring unexpected epoll events 0x%x on wake event fd.", epollEvents);
            }
        } else {
            ssize_t requestIndex = mRequests.indexOfKey(fd);
            if (requestIndex >= 0) {
                int events = 0;
                if (epollEvents & EPOLLIN) events |= EVENT_INPUT;
                if (epollEvents & EPOLLOUT) events |= EVENT_OUTPUT;
                if (epollEvents & EPOLLERR) events |= EVENT_ERROR;
                if (epollEvents & EPOLLHUP) events |= EVENT_HANGUP;
                pushResponse(events, mRequests.valueAt(requestIndex));
            } else {
                ALOGW("Ignoring unexpected epoll events 0x%x on fd %d that is "
                        "no longer registered.", epollEvents, fd);
            }
        }
    }
Done: ;

//这里是响应C++层的Handler消息,暂且不管
......
    return result;
}

epoll_wait接触等待在这里有两个操作途径,一个是将等待时间设置为0, 即java层的

nextPollTimeoutMillis = 0;

另一个是在

nextPollTimeoutMillis = -1;

的情况下,调用nativeWake,这个方法最终调用到了:

Looper.cpp中的：

void Looper::wake() {
#if DEBUG_POLL_AND_WAKE
    ALOGD("%p ~ wake", this);
#endif

    uint64_t inc = 1;
    //write方法是写入了一个wake标志唤醒epoll_wair等待， 其实就是不断写入一个无用数据直到成功，来唤醒epoll_wait。
    ssize_t nWrite = TEMP_FAILURE_RETRY(write(mWakeEventFd, &inc, sizeof(uint64_t)));
    if (nWrite != sizeof(uint64_t)) {
        if (errno != EAGAIN) {
            ALOGW("Could not write wake signal: %s", strerror(errno));
        }
    }
}

rebuildEpollLocked： 设置mWakeEventFd事件监听：

void Looper::rebuildEpollLocked() {
    // Close old epoll instance if we have one.
    if (mEpollFd >= 0) {
#if DEBUG_CALLBACKS
        ALOGD("%p ~ rebuildEpollLocked - rebuilding epoll set", this);
#endif
        close(mEpollFd);
    }

    // Allocate the new epoll instance and register the wake pipe.
    mEpollFd = epoll_create(EPOLL_SIZE_HINT);
    LOG_ALWAYS_FATAL_IF(mEpollFd < 0, "Could not create epoll instance: %s", strerror(errno));

    struct epoll_event eventItem;
    memset(& eventItem, 0, sizeof(epoll_event)); // zero out unused members of data field union
    eventItem.events = EPOLLIN;
    eventItem.data.fd = mWakeEventFd;
    //这里为epoll添加了mWakeEventFd事件的监听, 监听mWakeEventFd是否有数据到来,如果有就返回,即被唤醒
    int result = epoll_ctl(mEpollFd, EPOLL_CTL_ADD, mWakeEventFd, & eventItem);
    LOG_ALWAYS_FATAL_IF(result != 0, "Could not add wake event fd to epoll instance: %s",
                        strerror(errno));

......
}

总结：

Barrier

MessageQueue中可以设置Barrier（屏障）， 来阻止Barrier设置的时间点之后的同步Message执行，直到调用removeSyncBarrier被调用：

Barrier的实质是一个tartget（Handler）为空的Message对象。

返回值是当前设置的barrier的token， 这个用来在调用removeSyncBarrier的时候作为参数来取消对应的MessageQueue中的Barrier。

int enqueueSyncBarrier(long when) {
    // Enqueue a new sync barrier token.
    // We don't need to wake the queue because the purpose of a barrier is to stall it.
    synchronized (this) {
        final int token = mNextBarrierToken++;
        //创建一个tartget为null（未设置tartget）的msg作为barrier
        final Message msg = Message.obtain();
        msg.markInUse();
        msg.when = when;
        msg.arg1 = token;

        Message prev = null;
        Message p = mMessages;
        if (when != 0) {
            //执行时间在barrier之前的message不会被阻止执行.
            while (p != null && p.when <= when) {
                prev = p;
                p = p.next;
            }
        }
        if (prev != null) { // invariant: p == prev.next
            //如果有将要执行的message(行时间在barrier之前),会将barrier放在这个message之后,这个message不会被阻止执行
            msg.next = p;
            prev.next = msg;
        } else {
            //没有将要执行的message, 则直接将barrier放在头部,后面的message都不会被执行,直到调用removeSyncBarrier
            msg.next = p;
            mMessages = msg;
        }
        return token;
    }
}

removeSyncBarrier：

void removeSyncBarrier(int token) {
    // Remove a sync barrier token from the queue.
    // If the queue is no longer stalled by a barrier then wake it.
    synchronized (this) {
        Message prev = null;
        Message p = mMessages;
        while (p != null && (p.target != null || p.arg1 != token)) {
            prev = p;
            p = p.next;
        }
        if (p == null) {
            throw new IllegalStateException("The specified message queue synchronization "
                    + " barrier token has not been posted or has already been removed.");
        }
        final boolean needWake;
        if (prev != null) {
            prev.next = p.next;
            needWake = false;
        } else {
            mMessages = p.next;
            needWake = mMessages == null || mMessages.target != null;
        }
        p.recycleUnchecked();

        // If the loop is quitting then it is already awake.
        // We can assume mPtr != 0 when mQuitting is false.
        if (needWake && !mQuitting) {
            nativeWake(mPtr);
        }
    }
}