Handler续谈（epoll）

提起handler我们就不得不谈epoll

epoll的主要机制是：

1）调用epoll_create()建立一个epoll对象(在epoll文件系统中为这个句柄对象分配资源)

2）调用epoll_ctl向epoll对象中添加事件的套接字

3）调用epoll_wait收集发生的事件的连接

从Android 2.3开始，Google把Handler的阻塞/唤醒方案从Object#wait()/notify()改成了用Linux epoll来实现。原因是Native层也需要引入一套消息管理机制用于提供给C/C++开发者使用，而现有的阻塞/唤醒方案是为Java层准备的，只支持Java。因此从Android 2.3开始在Native层重新实现了一套阻塞/唤醒方案，Java层弃用Object#wait()/notify()，改为通过jni调用Native进入阻塞态。

接下来我们通过代码来理解

首先我们肯定要先创建消息队列来存放message

我们看下准备方法 在这个ActivityThread类

  public static void main(String[] args) {
        Trace.traceBegin(Trace.TRACE_TAG_ACTIVITY_MANAGER, "ActivityThreadMain");

        // Install selective syscall interception
        AndroidOs.install();

        // CloseGuard defaults to true and can be quite spammy.  We
        // disable it here, but selectively enable it later (via
        // StrictMode) on debug builds, but using DropBox, not logs.
        CloseGuard.setEnabled(false);

        Environment.initForCurrentUser();

        // Make sure TrustedCertificateStore looks in the right place for CA certificates
        final File configDir = Environment.getUserConfigDirectory(UserHandle.myUserId());
        TrustedCertificateStore.setDefaultUserDirectory(configDir);

        // Call per-process mainline module initialization.
        initializeMainlineModules();

        Process.setArgV0("<pre-initialized>");

        Looper.prepareMainLooper();

Looper.prepareMainLooper();这个方法是我们的关注点

    public static void prepareMainLooper() {
        prepare(false);
        synchronized (Looper.class) {
            if (sMainLooper != null) {
                throw new IllegalStateException("The main Looper has already been prepared.");
            }
            sMainLooper = myLooper();
        }
    }

这个方法主要是确保looper的唯一性，我们看下prepare方法

    private static void prepare(boolean quitAllowed) {
        if (sThreadLocal.get() != null) {
            throw new RuntimeException("Only one Looper may be created per thread");
        }
        sThreadLocal.set(new Looper(quitAllowed));
    }

我们看下looper的构造方法

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

我们看下队列的实现方法，

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

这里调用了native方法，我们看下实现

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<jlong>(nativeMessageQueue);
}

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

根据头文件我们也可以看出这里的looper是c++实现的，并非java，第一次肯定为空调用

Looper::Looper(bool allowNonCallbacks)
    : mAllowNonCallbacks(allowNonCallbacks),
      mSendingMessage(false),
      mPolling(false),
      mEpollRebuildRequired(false),
      mNextRequestSeq(WAKE_EVENT_FD_SEQ + 1),
      mResponseIndex(0),
      mNextMessageUptime(LLONG_MAX) {
    mWakeEventFd.reset(eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC));
    LOG_ALWAYS_FATAL_IF(mWakeEventFd.get() < 0, "Could not make wake event fd: %s", strerror(errno));

    AutoMutex _l(mLock);
    rebuildEpollLocked();
}

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
        mEpollFd.reset();
    }

    // Allocate the new epoll instance and register the WakeEventFd.
    mEpollFd.reset(epoll_create1(EPOLL_CLOEXEC));
    LOG_ALWAYS_FATAL_IF(mEpollFd < 0, "Could not create epoll instance: %s", strerror(errno));

    epoll_event wakeEvent = createEpollEvent(EPOLLIN, WAKE_EVENT_FD_SEQ);
    int result = epoll_ctl(mEpollFd.get(), EPOLL_CTL_ADD, mWakeEventFd.get(), &wakeEvent);
    LOG_ALWAYS_FATAL_IF(result != 0, "Could not add wake event fd to epoll instance: %s",
                        strerror(errno));

    for (const auto& [seq, request] : mRequests) {
        epoll_event eventItem = createEpollEvent(request.getEpollEvents(), seq);

        int epollResult = epoll_ctl(mEpollFd.get(), EPOLL_CTL_ADD, request.fd, &eventItem);
        if (epollResult < 0) {
            ALOGE("Error adding epoll events for fd %d while rebuilding epoll set: %s",
                  request.fd, strerror(errno));
        }
    }
}

这里调用了epoll_create1，epoll实例也就被创建了

创建之后就该使用了，看下流程，我们肯定调用Looper.loop()，来等待方法

    public static void loop() {
        final Looper me = myLooper();
        if (me == null) {
            throw new RuntimeException("No Looper; Looper.prepare() wasn't called on this thread.");
        }
        if (me.mInLoop) {
            Slog.w(TAG, "Loop again would have the queued messages be executed"
                    + " before this one completed.");
        }

        me.mInLoop = true;

        // 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();

        // Allow overriding a threshold with a system prop. e.g.
        // adb shell 'setprop log.looper.1000.main.slow 1 && stop && start'
        final int thresholdOverride =
                SystemProperties.getInt("log.looper."
                        + Process.myUid() + "."
                        + Thread.currentThread().getName()
                        + ".slow", -1);

        me.mSlowDeliveryDetected = false;

        for (;;) {
            if (!loopOnce(me, ident, thresholdOverride)) {
                return;
            }
        }
    }

我们看下loopOnce实现

    @SuppressWarnings({"UnusedTokenOfOriginalCallingIdentity",
            "ClearIdentityCallNotFollowedByTryFinally"})
    private static boolean loopOnce(final Looper me,
            final long ident, final int thresholdOverride) {
        Message msg = me.mQueue.next(); // might block
        if (msg == null) {
            // No message indicates that the message queue is quitting.
            return false;
        }

        // This must be in a local variable, in case a UI event sets the logger
        final Printer logging = me.mLogging;
        if (logging != null) {
            logging.println(">>>>> Dispatching to " + msg.target + " "
                    + msg.callback + ": " + msg.what);
        }
        // Make sure the observer won't change while processing a transaction.
        final Observer observer = sObserver;

        final long traceTag = me.mTraceTag;
        long slowDispatchThresholdMs = me.mSlowDispatchThresholdMs;
        long slowDeliveryThresholdMs = me.mSlowDeliveryThresholdMs;

        final boolean hasOverride = thresholdOverride >= 0;
        if (hasOverride) {
            slowDispatchThresholdMs = thresholdOverride;
            slowDeliveryThresholdMs = thresholdOverride;
        }
        final boolean logSlowDelivery = (slowDeliveryThresholdMs > 0 || hasOverride)
                && (msg.when > 0);
        final boolean logSlowDispatch = (slowDispatchThresholdMs > 0 || hasOverride);

        final boolean needStartTime = logSlowDelivery || logSlowDispatch;
        final boolean needEndTime = logSlowDispatch;

        if (traceTag != 0 && Trace.isTagEnabled(traceTag)) {
            Trace.traceBegin(traceTag, msg.target.getTraceName(msg));
        }

        final long dispatchStart = needStartTime ? SystemClock.uptimeMillis() : 0;
        final long dispatchEnd;
        Object token = null;
        if (observer != null) {
            token = observer.messageDispatchStarting();
        }
        long origWorkSource = ThreadLocalWorkSource.setUid(msg.workSourceUid);
        try {
            msg.target.dispatchMessage(msg);
            if (observer != null) {
                observer.messageDispatched(token, msg);
            }
            dispatchEnd = needEndTime ? SystemClock.uptimeMillis() : 0;
        } catch (Exception exception) {
            if (observer != null) {
                observer.dispatchingThrewException(token, msg, exception);
            }
            throw exception;
        } finally {
            ThreadLocalWorkSource.restore(origWorkSource);
            if (traceTag != 0) {
                Trace.traceEnd(traceTag);
            }
        }
        if (logSlowDelivery) {
            if (me.mSlowDeliveryDetected) {
                if ((dispatchStart - msg.when) <= 10) {
                    Slog.w(TAG, "Drained");
                    me.mSlowDeliveryDetected = false;
                }
            } else {
                if (showSlowLog(slowDeliveryThresholdMs, msg.when, dispatchStart, "delivery",
                        msg)) {
                    // Once we write a slow delivery log, suppress until the queue drains.
                    me.mSlowDeliveryDetected = true;
                }
            }
        }
        if (logSlowDispatch) {
            showSlowLog(slowDispatchThresholdMs, dispatchStart, dispatchEnd, "dispatch", 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();

        return true;
    }

epoll主要是用来消息处理的，我们看下消息的获得方法  Message msg = me.mQueue.next();

  @UnsupportedAppUsage
    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;
        }

        int pendingIdleHandlerCount = -1; // -1 only during first iteration
        int nextPollTimeoutMillis = 0;
        for (;;) {
            if (nextPollTimeoutMillis != 0) {
                Binder.flushPendingCommands();
            }

            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) {

里面调用了nativePollOnce，消息没有到指定时间就会阻塞住

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

最后由调用到looper

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 DEBUG_POLL_AND_WAKE
                ALOGD("%p ~ pollOnce - returning signalled identifier %d: "
                        "fd=%d, events=0x%x, data=%p",
                        this, ident, fd, events, data);
#endif
                if (outFd != nullptr) *outFd = fd;
                if (outEvents != nullptr) *outEvents = events;
                if (outData != nullptr) *outData = data;
                return ident;
            }
        }

        if (result != 0) {
#if DEBUG_POLL_AND_WAKE
            ALOGD("%p ~ pollOnce - returning result %d", this, result);
#endif
            if (outFd != nullptr) *outFd = 0;
            if (outEvents != nullptr) *outEvents = 0;
            if (outData != nullptr) *outData = nullptr;
            return result;
        }

        result = pollInner(timeoutMillis);
    }
}

之后处理完交给pollInner

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

    // No longer idling.
    mPolling = false;

    // Acquire lock.
    mLock.lock();

最后又调用到关键方法epoll_wait来等待。