Netty(二)：io请求处理过程解析

文接上一篇。上篇讲到netty暴露一个端口出来，acceptor, handler, pipeline, eventloop 都已准备好。但是并没体现其如何处理接入新的网络请求，今天我们就一起来看看吧。

1. eventloop主循环

　　上篇讲到，netty启动起来之后，就会有很多个eventloop线程会一直在循环工作（server通用特性），比如进行select或者执行task. 我们再来回顾 NioEventLoop 的实现方式吧！

　　我们先看看下 NioEventLoop 的类图吧：

 　　看起来非常复杂，不管它。它核心方法自然是 run();

   // io.netty.channel.nio.NioEventLoop#run
    @Override
    protected void run() {
        // 一个死循环检测任务, 这就 eventloop 的大杀器哦
        for (;;) {
            try {
                switch (selectStrategy.calculateStrategy(selectNowSupplier, hasTasks())) {
                    case SelectStrategy.CONTINUE:
                        continue;
                    // 有任务时执行任务, 否则阻塞等待网络事件, 或被唤醒
                    case SelectStrategy.SELECT:
                        // select.select(), 带超时限制
                        select(wakenUp.getAndSet(false));

                        // 'wakenUp.compareAndSet(false, true)' is always evaluated
                        // before calling 'selector.wakeup()' to reduce the wake-up
                        // overhead. (Selector.wakeup() is an expensive operation.)
                        //
                        // However, there is a race condition in this approach.
                        // The race condition is triggered when 'wakenUp' is set to
                        // true too early.
                        //
                        // 'wakenUp' is set to true too early if:
                        // 1) Selector is waken up between 'wakenUp.set(false)' and
                        //    'selector.select(...)'. (BAD)
                        // 2) Selector is waken up between 'selector.select(...)' and
                        //    'if (wakenUp.get()) { ... }'. (OK)
                        //
                        // In the first case, 'wakenUp' is set to true and the
                        // following 'selector.select(...)' will wake up immediately.
                        // Until 'wakenUp' is set to false again in the next round,
                        // 'wakenUp.compareAndSet(false, true)' will fail, and therefore
                        // any attempt to wake up the Selector will fail, too, causing
                        // the following 'selector.select(...)' call to block
                        // unnecessarily.
                        //
                        // To fix this problem, we wake up the selector again if wakenUp
                        // is true immediately after selector.select(...).
                        // It is inefficient in that it wakes up the selector for both
                        // the first case (BAD - wake-up required) and the second case
                        // (OK - no wake-up required).

                        if (wakenUp.get()) {
                            selector.wakeup();
                        }
                        // fall through
                    default:
                }

                cancelledKeys = 0;
                needsToSelectAgain = false;
                // ioRatio 为io操作的占比, 和运行任务相比, 默认为 50:50
                final int ioRatio = this.ioRatio;
                if (ioRatio == 100) {
                    try {
                        // step1. 运行io操作
                        processSelectedKeys();
                    } finally {
                        // Ensure we always run tasks.
                        // step2. 运行task任务
                        runAllTasks();
                    }
                } else {
                    final long ioStartTime = System.nanoTime();
                    try {
                        processSelectedKeys();
                    } finally {
                        // Ensure we always run tasks.
                        final long ioTime = System.nanoTime() - ioStartTime;
                        // 运行任务的最长时间
                        runAllTasks(ioTime * (100 - ioRatio) / ioRatio);
                    }
                }
            } catch (Throwable t) {
                handleLoopException(t);
            }
            // Always handle shutdown even if the loop processing threw an exception.
            try {
                if (isShuttingDown()) {
                    closeAll();
                    if (confirmShutdown()) {
                        return;
                    }
                }
            } catch (Throwable t) {
                handleLoopException(t);
            }
        }
    }
    // select, 事件循环的依据
    private void select(boolean oldWakenUp) throws IOException {
        Selector selector = this.selector;
        try {
            int selectCnt = 0;
            long currentTimeNanos = System.nanoTime();
            // 带超时限制, 默认最大超时1s, 但当有延时任务处理时, 以它为标准
            long selectDeadLineNanos = currentTimeNanos + delayNanos(currentTimeNanos);

            for (;;) {
                long timeoutMillis = (selectDeadLineNanos - currentTimeNanos + 500000L) / 1000000L;
                if (timeoutMillis <= 0) {
                    // 超时则立即返回
                    if (selectCnt == 0) {
                        selector.selectNow();
                        selectCnt = 1;
                    }
                    break;
                }

                // If a task was submitted when wakenUp value was true, the task didn't get a chance to call
                // Selector#wakeup. So we need to check task queue again before executing select operation.
                // If we don't, the task might be pended until select operation was timed out.
                // It might be pended until idle timeout if IdleStateHandler existed in pipeline.
                if (hasTasks() && wakenUp.compareAndSet(false, true)) {
                    selector.selectNow();
                    selectCnt = 1;
                    break;
                }

                int selectedKeys = selector.select(timeoutMillis);
                selectCnt ++;

                if (selectedKeys != 0 || oldWakenUp || wakenUp.get() || hasTasks() || hasScheduledTasks()) {
                    // - Selected something,
                    // - waken up by user, or
                    // - the task queue has a pending task.
                    // - a scheduled task is ready for processing
                    break;
                }
                if (Thread.interrupted()) {
                    // Thread was interrupted so reset selected keys and break so we not run into a busy loop.
                    // As this is most likely a bug in the handler of the user or it's client library we will
                    // also log it.
                    //
                    // See https://github.com/netty/netty/issues/2426
                    if (logger.isDebugEnabled()) {
                        logger.debug("Selector.select() returned prematurely because " +
                                "Thread.currentThread().interrupt() was called. Use " +
                                "NioEventLoop.shutdownGracefully() to shutdown the NioEventLoop.");
                    }
                    selectCnt = 1;
                    break;
                }

                long time = System.nanoTime();
                if (time - TimeUnit.MILLISECONDS.toNanos(timeoutMillis) >= currentTimeNanos) {
                    // timeoutMillis elapsed without anything selected.
                    selectCnt = 1;
                } else if (SELECTOR_AUTO_REBUILD_THRESHOLD > 0 &&
                        selectCnt >= SELECTOR_AUTO_REBUILD_THRESHOLD) {
                    // The selector returned prematurely many times in a row.
                    // Rebuild the selector to work around the problem.
                    logger.warn(
                            "Selector.select() returned prematurely {} times in a row; rebuilding Selector {}.",
                            selectCnt, selector);

                    rebuildSelector();
                    selector = this.selector;

                    // Select again to populate selectedKeys.
                    selector.selectNow();
                    selectCnt = 1;
                    break;
                }

                currentTimeNanos = time;
            }

            if (selectCnt > MIN_PREMATURE_SELECTOR_RETURNS) {
                if (logger.isDebugEnabled()) {
                    logger.debug("Selector.select() returned prematurely {} times in a row for Selector {}.",
                            selectCnt - 1, selector);
                }
            }
        } catch (CancelledKeyException e) {
            if (logger.isDebugEnabled()) {
                logger.debug(CancelledKeyException.class.getSimpleName() + " raised by a Selector {} - JDK bug?",
                        selector, e);
            }
            // Harmless exception - log anyway
        }
    }

　　大体来说就是：eventloop是一个一直在运行的线程，它会不停地检测是否发生了网络事件或者被提交上来了新任务，如果有那么就会去执行这些任务。

　　在处理io事件和task时，为防止调度的饥饿问题，它设置了一个ioRatio来避免发生。即如果io事件占用了ioTime时间，那么task也应该占用相应剩下比例的时间，以保持公平性。

　　在实现上，发现网络io事件是通过 selector.select()的，而发现task任务是通过 hasTasks()来实现检测的。每检测一次，一般不超过1s的休眠时间，以免在特殊情况下发生意外而导致系统假死。

2. acceptor 运行io操作

　　io操作主要就是监控一些网络事件，比如新连接请求，请请求，写请求，关闭请求等。它是一个网络应用的非常核心的功能之一。从eventloop的核心循环中，我们看到其 processSelectedKeys() 就做网络io事件处理的。

 // io.netty.channel.nio.NioEventLoop#processSelectedKeys
    private void processSelectedKeys() {
        // selectedKeys 为前面进行bind()时初始化掉的，所以不会为空
        if (selectedKeys != null) {
            processSelectedKeysOptimized();
        } else {
            processSelectedKeysPlain(selector.selectedKeys());
        }
    }
    
    private void processSelectedKeysOptimized() {
        // 当无网络事件发生时，selectedKeys.size=0, 不会发生处理行为
        for (int i = 0; i < selectedKeys.size; ++i) {
            // 当有网络事件发生时，selectedKeys 为各就绪事件
            final SelectionKey k = selectedKeys.keys[i];
            // null out entry in the array to allow to have it GC'ed once the Channel close
            // See https://github.com/netty/netty/issues/2363
            selectedKeys.keys[i] = null;

            final Object a = k.attachment();

            if (a instanceof AbstractNioChannel) {
                // 转换成相应的channel, 调用
                processSelectedKey(k, (AbstractNioChannel) a);
            } else {
                @SuppressWarnings("unchecked")
                NioTask<SelectableChannel> task = (NioTask<SelectableChannel>) a;
                processSelectedKey(k, task);
            }

            if (needsToSelectAgain) {
                // null out entries in the array to allow to have it GC'ed once the Channel close
                // See https://github.com/netty/netty/issues/2363
                selectedKeys.reset(i + 1);

                selectAgain();
                i = -1;
            }
        }
    }
    // 处理具体的socket
    private void processSelectedKey(SelectionKey k, AbstractNioChannel ch) {
        final AbstractNioChannel.NioUnsafe unsafe = ch.unsafe();
        // 
        if (!k.isValid()) {
            final EventLoop eventLoop;
            try {
                eventLoop = ch.eventLoop();
            } catch (Throwable ignored) {
                // If the channel implementation throws an exception because there is no event loop, we ignore this
                // because we are only trying to determine if ch is registered to this event loop and thus has authority
                // to close ch.
                return;
            }
            // Only close ch if ch is still registered to this EventLoop. ch could have deregistered from the event loop
            // and thus the SelectionKey could be cancelled as part of the deregistration process, but the channel is
            // still healthy and should not be closed.
            // See https://github.com/netty/netty/issues/5125
            if (eventLoop != this || eventLoop == null) {
                return;
            }
            // close the channel if the key is not valid anymore
            unsafe.close(unsafe.voidPromise());
            return;
        }

        try {
            // 取出就绪事件类型进行判断
            int readyOps = k.readyOps();
            // We first need to call finishConnect() before try to trigger a read(...) or write(...) as otherwise
            // the NIO JDK channel implementation may throw a NotYetConnectedException.
            // 如果是连接事件，则先进行连接操作，触发 finishConnect() 事件链
            if ((readyOps & SelectionKey.OP_CONNECT) != 0) {
                // remove OP_CONNECT as otherwise Selector.select(..) will always return without blocking
                // See https://github.com/netty/netty/issues/924
                int ops = k.interestOps();
                ops &= ~SelectionKey.OP_CONNECT;
                k.interestOps(ops);

                unsafe.finishConnect();
            }

            // Process OP_WRITE first as we may be able to write some queued buffers and so free memory.
            // 如果是写事件，则强制channel写数据
            if ((readyOps & SelectionKey.OP_WRITE) != 0) {
                // Call forceFlush which will also take care of clear the OP_WRITE once there is nothing left to write
                ch.unsafe().forceFlush();
            }

            // Also check for readOps of 0 to workaround possible JDK bug which may otherwise lead
            // to a spin loop
            if ((readyOps & (SelectionKey.OP_READ | SelectionKey.OP_ACCEPT)) != 0 || readyOps == 0) {
                // 读取数据, OP_READ, OP_ACCEPT 会进入到此处，事件处理从此开始
                unsafe.read();
            }
        } catch (CancelledKeyException ignored) {
            unsafe.close(unsafe.voidPromise());
        }
    }
        // io.netty.channel.nio.AbstractNioMessageChannel.NioMessageUnsafe#read
        @Override
        public void read() {
            // 此处断言，只有io线程本身才可以进行read()操作，如果被其他线程执行，那就是有问题的
            assert eventLoop().inEventLoop();
            // 取出config, Pipeline...
            final ChannelConfig config = config();
            final ChannelPipeline pipeline = pipeline();
            // 调用 allocator 分配接收内存, io.netty.channel.AdaptiveRecvByteBufAllocator.HandleImpl
            // 并重置读取状态
            final RecvByteBufAllocator.Handle allocHandle = unsafe().recvBufAllocHandle();
            allocHandle.reset(config);

            boolean closed = false;
            Throwable exception = null;
            try {
                try {