深入理解MessageQueue

Android 中有两个非常重要的知识点，分别是Binder机制和Handler机制。前者用于跨进程通讯，并且通过 ServiceManager 给上层应用提供了大量的服务，而后者用于进程内部通讯，以消息队列的形式驱动应用的运行。之前的文章已经多次分析了Binder相关的内容，复杂程度远高于Handler，之后还会继续分析Binder。说到Handler，做安卓开发的一定都不会陌生，一般用于切换线程。其涉及到的类还有Looper，MessageQueue，Message 等。其中MessageQueue是事件驱动的基础，本文会重点分析MessageQueue，其他内容会简单带过，可以参考生产者-消费者模式。

从Handler的入口开始分析：

 Looper.prepare(); 

1.创建一个Looper，并且是线程私有的：sThreadLocal.set(new Looper(quitAllowed));
2.初始化Handler：mHandler = new Handler();，在构造函数中会获取线程私有的Looper，如获取不到会报错。
3.开启无限循环：Looper.loop();。
在loop方法中主要代码如下：

 for (;;) { Message msg = queue.next(); // might block if (msg == null) { // No message indicates that the message queue is quitting. return; } msg.target.dispatchMessage(msg); msg.recycleUnchecked(); } 

1. 从MessageQueue中获取待处理的Message（阻塞线程）
2. 交给与之关联的Handler处理
3. 回收Message，供Message.obtain()复用

其中msg中的target是在Handler发送消息的时候赋值的：

 public boolean sendMessageAtTime(Message msg, long uptimeMillis) { MessageQueue queue = mQueue; if (queue == null) { RuntimeException e = new RuntimeException this + " sendMessageAtTime() called with no mQueue"); return false; } return enqueueMessage(queue, msg, uptimeMillis); } private boolean enqueueMessage(MessageQueue queue, Message msg, long uptimeMillis) { msg.target = this; if (mAsynchronous) { msg.setAsynchronous(true); } return queue.enqueueMessage(msg, uptimeMillis); } 

1. 创建与线程绑定的Looper，同时会创建一个与之关联的MessageQueue用于存放消息
2. 开启消息循环，从MessageQueue中获取待处理消息，若无消息会阻塞线程
3. 通过Handler发送消息，此时会将Message入队列到MessageQueue中，并且唤醒等待的Looper
4. Looper获取的消息会投递给对应的Handler处理

 MessageQueue(boolean quitAllowed) { mQuitAllowed = quitAllowed; mPtr = nativeInit(); } 

 static jlong android_os_MessageQueue_nativeInit(JNIEnv* env, jclass clazz) { NativeMessageQueue* nativeMessageQueue = new NativeMessageQueue(); if (!nativeMessageQueue) { jniThrowRuntimeException(env, "Unable to allocate native queue"); return 0; } nativeMessageQueue->incStrong(env); return reinterpret_cast(nativeMessageQueue); } 

 NativeMessageQueue::NativeMessageQueue() : mPollEnv(NULL), mPollObj(NULL), mExceptionObj(NULL) { mLooper = Looper::getForThread(); if (mLooper == NULL) { mLooper = new Looper(false); Looper::setForThread(mLooper); } } 

 Message next() { final long ptr = mPtr; if (ptr == 0) { return null; } int pendingIdleHandlerCount = -1; // -1 only during first iteration int nextPollTimeoutMillis = 0; for (;;) { nativePollOnce(ptr, nextPollTimeoutMillis); synchronized (this) { // Try to retrieve the next message. Return if found. final long now = SystemClock.uptimeMillis(); Message prevMsg = null; Message msg = mMessages; if (msg != null && msg.target == null) { // Stalled by a barrier. Find the next asynchronous message in the queue. do { prevMsg = msg; msg = msg.next; } while (msg != null && !msg.isAsynchronous()); } 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. mBlocked = false; if (prevMsg != null) { prevMsg.next = msg.next; } else { mMessages = msg.next; } msg.next = null; if (DEBUG) Log.v(TAG, "Returning message: " + msg); msg.markInUse(); return msg; } } else { // No more messages. nextPollTimeoutMillis = -1; } // Process the quit message now that all pending messages have been handled. if (mQuitting) { dispose(); return null; } } pendingIdleHandlerCount = 0; nextPollTimeoutMillis = 0; } } 

 private int postSyncBarrier(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++; final Message msg = Message.obtain(); msg.markInUse(); msg.when = when; msg.arg1 = token; Message prev = null; Message p = mMessages; if (when != 0) { while (p != null && p.when <= when) { prev = p; p = p.next; } } if (prev != null) { // invariant: p == prev.next msg.next = p; prev.next = msg; } else { msg.next = p; mMessages = msg; } return token; } } 

 boolean enqueueMessage(Message msg, long when) { synchronized (this) { msg.markInUse(); msg.when = when; Message p = mMessages; boolean needWake; if (p == null || when == 0 || when < p.when) { msg.next = p; mMessages = msg; needWake = mBlocked; } else { needWake = mBlocked && p.target == null && msg.isAsynchronous(); Message prev; for (;;) { prev = p; p = p.next; if (p == null || when < p.when) { break; } if (needWake && p.isAsynchronous()) { needWake = false; } } msg.next = p; // invariant: p == prev.next prev.next = msg; } if (needWake) { nativeWake(mPtr); } } return true; } 

上面的代码主要就是加入链表的时候按时间顺序从小到大排序，然后判断是否需要唤醒，如果需要唤醒则调用nativeWake(mPtr);来唤醒之前等待的线程。
再总结一下MessageQueue获取消息和加入消息的逻辑：
获取消息：
1.首次进入循环nextPollTimeoutMillis=0，阻塞方法nativePollOnce(ptr, nextPollTimeoutMillis)会立即返回
2.读取列表中的消息，如果发现消息屏障，则跳过后面的同步消息，总之会通过当前时间，是否遇到屏障来返回符合条件的待处理消息
3.如果没有符合条件的消息，会处理一些不紧急的任务（IdleHandler），再次进入第一步
加入消息：
1.加入消息比较简单，按时间顺序插入到消息链表中，如果是第一个那么根据mBlocked判断是否需要唤醒线程，如果不是第一个一般情况下不需要唤醒（如果加入的消息是异步的需要另外判断）
到这里其实关于MessageQueue已经分析的差不多了，其中有两个native方法没有涉及到分别是nativePollOnce，nativeWake，其实之前结论已经给出了，两个方法都会传入mPtr,在native层对应的是NativeMessageQueue的引用地址。
感兴趣的可以继续往下看，先看一下nativePollOnce的实现：
[android_os_MessageQueue.cpp]

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

 void NativeMessageQueue::pollOnce(JNIEnv* env, jobject pollObj, int timeoutMillis) { mPollEnv = env; mPollObj = pollObj; mLooper->pollOnce(timeoutMillis); mPollObj = NULL; mPollEnv = NULL; if (mExceptionObj) { env->Throw(mExceptionObj); env->DeleteLocalRef(mExceptionObj); mExceptionObj = NULL; } } 

 int Looper::pollOnce(int timeoutMillis, int* outFd, int* outEvents, void outData) { int result = 0; for (;;) { while (mResponseIndex < mResponses.size()) { const Response& response = mResponses.itemAt(mResponseIndex++); int ident = response.request.ident; if (ident >= 0) { int fd = response.request.fd; int events = response.events; void* data = response.request.data; if (outFd != NULL) *outFd = fd; if (outEvents != NULL) *outEvents = events; if (outData != NULL) *outData = data; return ident; } } if (result != 0) { if (outFd != NULL) *outFd = 0; if (outEvents != NULL) *outEvents = 0; if (outData != NULL) *outData = NULL; return result; } result = pollInner(timeoutMillis); } } 

先是处理native层的Response，这个直接跳过，最终调用pollInner

 int Looper::pollInner(int timeoutMillis) { // 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; } } // Poll. int result = POLL_WAKE; mResponses.clear(); mResponseIndex = 0; // We are about to idle. mPolling = true; struct epoll_event eventItems[EPOLL_MAX_EVENTS]; 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) { result = POLL_TIMEOUT; goto Done; } // Handle all events. 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: ; // Invoke pending message callbacks. mNextMessageUptime = LLONG_MAX; while (mMessageEnvelopes.size() != 0) { nsecs_t now = systemTime(SYSTEM_TIME_MONOTONIC); const MessageEnvelope& messageEnvelope = mMessageEnvelopes.itemAt(0); if (messageEnvelope.uptime <= now) { { // obtain handler sp handler = messageEnvelope.handler; Message message = messageEnvelope.message; mMessageEnvelopes.removeAt(0); mSendingMessage = true; mLock.unlock(); handler->handleMessage(message); } // release handler mLock.lock(); mSendingMessage = false; result = POLL_CALLBACK; } else { mNextMessageUptime = messageEnvelope.uptime; break; } } // Release lock. mLock.unlock(); // Invoke all response callbacks. for (size_t i = 0; i < mResponses.size(); i++) { Response& response = mResponses.editItemAt(i); if (response.request.ident == POLL_CALLBACK) { int fd = response.request.fd; int events = response.events; void* data = response.request.data; int callbackResult = response.request.callback->handleEvent(fd, events, data); if (callbackResult == 0) { removeFd(fd, response.request.seq); } response.request.callback.clear(); result = POLL_CALLBACK; } } return result; } 

这个方法有点长，首先会根据Native Message的信息计算此次需要等待的时间，再调用

int eventCount = epoll_wait(mEpollFd, eventItems, EPOLL_MAX_EVENTS, timeoutMillis);

 static void android_os_MessageQueue_nativeWake(JNIEnv* env, jclass clazz, jlong ptr) { NativeMessageQueue* nativeMessageQueue = reinterpret_cast 
   
     (ptr); nativeMessageQueue->wake(); } 
   

和之前一样，也是通过long类型的ptr获取NativeMessageQueue对象的指针，再调用wake方法：

 void NativeMessageQueue::wake() { mLooper->wake(); } 

调用的也是Looper的方法：

 void Looper::wake() { uint64_t inc = 1; 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)); } } } 

重点是write(mWakeEventFd, &inc, sizeof(uint64_t)),写入了一个1，这个时候epoll就能监听到事件，也就被唤醒了