作者:sprinkle_liz
所谓心跳, 即在 TCP 长连接中, 客户端和服务器之间定期发送的一种特殊的数据包, 通知对方自己还在线, 以确保 TCP 连接的有效性.
注:心跳包还有另一个作用,经常被忽略,即: 一个连接如果长时间不用,防火墙或者路由器就会断开该连接。
在 Netty 中, 实现心跳机制的关键是 IdleStateHandler, 那么这个 Handler 如何使用呢? 先看下它的构造器:
public IdleStateHandler(int readerIdleTimeSeconds, int writerIdleTimeSeconds, int allIdleTimeSeconds) { this((long)readerIdleTimeSeconds, (long)writerIdleTimeSeconds, (long)allIdleTimeSeconds, TimeUnit.SECONDS); }
这里解释下三个参数的含义:
注:这三个参数默认的时间单位是秒。若需要指定其他时间单位,可以使用另一个构造方法:IdleStateHandler(boolean observeOutput, long readerIdleTime, long writerIdleTime, long allIdleTime, TimeUnit unit)
在看下面的实现之前,建议先了解一下IdleStateHandler的实现原理。
下面直接上代码,需要注意的地方,会在代码中通过注释进行说明。
下面将使用IdleStateHandler来实现心跳,Client端连接到Server端后,会循环执行一个任务: 随机等待几秒 , 然后 ping 一下 Server 端 , 即发送一个心跳包 。当等待的时间超过规定时间,将会发送失败,以为Server端在此之前已经主动断开连接了。代码如下:
类ClientIdleStateTrigger也是一个Handler,只是重写了userEventTriggered方法,用于捕获IdleState.WRITER_IDLE事件(未在指定时间内向服务器发送数据),然后向Server端发送一个心跳包。
/** * <p> * 用于捕获{@link IdleState#WRITER_IDLE}事件(未在指定时间内向服务器发送数据),然后向<code>Server</code>端发送一个心跳包。 * </p> */ public class ClientIdleStateTrigger extends ChannelInboundHandlerAdapter { public static final String HEART_BEAT = "heart beat!"; @Override public void userEventTriggered(ChannelHandlerContext ctx, Object evt) throws Exception { if (evt instanceof IdleStateEvent) { IdleState state = ((IdleStateEvent) evt).state(); if (state == IdleState.WRITER_IDLE) { // write heartbeat to server ctx.writeAndFlush(HEART_BEAT); } } else { super.userEventTriggered(ctx, evt); } } }
/** * <p>客户端连接到服务器端后,会循环执行一个任务:随机等待几秒,然后ping一下Server端,即发送一个心跳包。</p> */ public class Pinger extends ChannelInboundHandlerAdapter { private Random random = new Random(); private int baseRandom = 8; private Channel channel; @Override public void channelActive(ChannelHandlerContext ctx) throws Exception { super.channelActive(ctx); this.channel = ctx.channel(); ping(ctx.channel()); } private void ping(Channel channel) { int second = Math.max(1, random.nextInt(baseRandom)); System.out.println("next heart beat will send after " + second + "s."); ScheduledFuture<?> future = channel.eventLoop().schedule(new Runnable() { @Override public void run() { if (channel.isActive()) { System.out.println("sending heart beat to the server..."); channel.writeAndFlush(ClientIdleStateTrigger.HEART_BEAT); } else { System.err.println("The connection had broken, cancel the task that will send a heart beat."); channel.closeFuture(); throw new RuntimeException(); } } }, second, TimeUnit.SECONDS); future.addListener(new GenericFutureListener() { @Override public void operationComplete(Future future) throws Exception { if (future.isSuccess()) { ping(channel); } } }); } @Override public void exceptionCaught(ChannelHandlerContext ctx, Throwable cause) throws Exception { // 当Channel已经断开的情况下, 仍然发送数据, 会抛异常, 该方法会被调用. cause.printStackTrace(); ctx.close(); } }
public class ClientHandlersInitializer extends ChannelInitializer<SocketChannel> { private ReconnectHandler reconnectHandler; private EchoHandler echoHandler; public ClientHandlersInitializer(TcpClient tcpClient) { Assert.notNull(tcpClient, "TcpClient can not be null."); this.reconnectHandler = new ReconnectHandler(tcpClient); this.echoHandler = new EchoHandler(); } @Override protected void initChannel(SocketChannel ch) throws Exception { ChannelPipeline pipeline = ch.pipeline(); pipeline.addLast(new LengthFieldBasedFrameDecoder(Integer.MAX_VALUE, 0, 4, 0, 4)); pipeline.addLast(new LengthFieldPrepender(4)); pipeline.addLast(new StringDecoder(CharsetUtil.UTF_8)); pipeline.addLast(new StringEncoder(CharsetUtil.UTF_8)); pipeline.addLast(new Pinger()); } }
注: 上面的Handler集合,除了Pinger,其他都是编解码器和解决粘包,可以忽略。
public class TcpClient { private String host; private int port; private Bootstrap bootstrap; /** 将<code>Channel</code>保存起来, 可用于在其他非handler的地方发送数据 */ private Channel channel; public TcpClient(String host, int port) { this(host, port, new ExponentialBackOffRetry(1000, Integer.MAX_VALUE, 60 * 1000)); } public TcpClient(String host, int port, RetryPolicy retryPolicy) { this.host = host; this.port = port; init(); } /** * 向远程TCP服务器请求连接 */ public void connect() { synchronized (bootstrap) { ChannelFuture future = bootstrap.connect(host, port); this.channel = future.channel(); } } private void init() { EventLoopGroup group = new NioEventLoopGroup(); // bootstrap 可重用, 只需在TcpClient实例化的时候初始化即可. bootstrap = new Bootstrap(); bootstrap.group(group) .channel(NioSocketChannel.class) .handler(new ClientHandlersInitializer(TcpClient.this)); } public static void main(String[] args) { TcpClient tcpClient = new TcpClient("localhost", 2222); tcpClient.connect(); } }
/** * <p>在规定时间内未收到客户端的任何数据包, 将主动断开该连接</p> */ public class ServerIdleStateTrigger extends ChannelInboundHandlerAdapter { @Override public void userEventTriggered(ChannelHandlerContext ctx, Object evt) throws Exception { if (evt instanceof IdleStateEvent) { IdleState state = ((IdleStateEvent) evt).state(); if (state == IdleState.READER_IDLE) { // 在规定时间内没有收到客户端的上行数据, 主动断开连接 ctx.disconnect(); } } else { super.userEventTriggered(ctx, evt); } } }
/** * <p>收到来自客户端的数据包后, 直接在控制台打印出来.</p> */ @ChannelHandler.Sharable public class ServerBizHandler extends SimpleChannelInboundHandler<String> { private final String REC_HEART_BEAT = "I had received the heart beat!"; @Override protected void channelRead0(ChannelHandlerContext ctx, String data) throws Exception { try { System.out.println("receive data: " + data); // ctx.writeAndFlush(REC_HEART_BEAT); } catch (Exception e) { e.printStackTrace(); } } @Override public void channelActive(ChannelHandlerContext ctx) throws Exception { System.out.println("Established connection with the remote client."); // do something ctx.fireChannelActive(); } @Override public void channelInactive(ChannelHandlerContext ctx) throws Exception { System.out.println("Disconnected with the remote client."); // do something ctx.fireChannelInactive(); } @Override public void exceptionCaught(ChannelHandlerContext ctx, Throwable cause) throws Exception { cause.printStackTrace(); ctx.close(); } }
/** * <p>用于初始化服务器端涉及到的所有<code>Handler</code></p> */ public class ServerHandlerInitializer extends ChannelInitializer<SocketChannel> { protected void initChannel(SocketChannel ch) throws Exception { ch.pipeline().addLast("idleStateHandler", new IdleStateHandler(5, 0, 0)); ch.pipeline().addLast("idleStateTrigger", new ServerIdleStateTrigger()); ch.pipeline().addLast("frameDecoder", new LengthFieldBasedFrameDecoder(Integer.MAX_VALUE, 0, 4, 0, 4)); ch.pipeline().addLast("frameEncoder", new LengthFieldPrepender(4)); ch.pipeline().addLast("decoder", new StringDecoder()); ch.pipeline().addLast("encoder", new StringEncoder()); ch.pipeline().addLast("bizHandler", new ServerBizHandler()); } }
注:new IdleStateHandler(5, 0, 0)该handler代表如果在5秒内没有收到来自客户端的任何数据包(包括但不限于心跳包),将会主动断开与该客户端的连接。
public class TcpServer { private int port; private ServerHandlerInitializer serverHandlerInitializer; public TcpServer(int port) { this.port = port; this.serverHandlerInitializer = new ServerHandlerInitializer(); } public void start() { EventLoopGroup bossGroup = new NioEventLoopGroup(1); EventLoopGroup workerGroup = new NioEventLoopGroup(); try { ServerBootstrap bootstrap = new ServerBootstrap(); bootstrap.group(bossGroup, workerGroup) .channel(NioServerSocketChannel.class) .childHandler(this.serverHandlerInitializer); // 绑定端口,开始接收进来的连接 ChannelFuture future = bootstrap.bind(port).sync(); System.out.println("Server start listen at " + port); future.channel().closeFuture().sync(); } catch (Exception e) { bossGroup.shutdownGracefully(); workerGroup.shutdownGracefully(); e.printStackTrace(); } } public static void main(String[] args) throws Exception { int port = 2222; new TcpServer(port).start(); } }
至此,所有代码已经编写完毕。
首先启动客户端,再启动服务器端。启动完成后,在客户端的控制台上,可以看到打印如下类似日志:
客户端控制台输出的日志
在服务器端可以看到控制台输出了类似如下的日志:
服务器端控制台输出的日志
可以看到,客户端在发送4个心跳包后,第5个包因为等待时间较长,等到真正发送的时候,发现连接已断开了;而服务器端收到客户端的4个心跳数据包后,迟迟等不到下一个数据包,所以果断断开该连接。
在测试过程中,有可能会出现如下情况:
异常情况
出现这种情况的原因是:在连接已断开的情况下,仍然向服务器端发送心跳包。虽然在发送心跳包之前会使用channel.isActive()判断连接是否可用,但也有可能上一刻判断结果为可用,但下一刻发送数据包之前,连接就断了。
目前尚未找到优雅处理这种情况的方案,各位看官如果有好的解决方案,还望不吝赐教。拜谢!!!
断线重连这里就不过多介绍,相信各位都知道是怎么回事。这里只说大致思路,然后直接上代码。
客户端在监测到与服务器端的连接断开后,或者一开始就无法连接的情况下,使用指定的重连策略进行重连操作,直到重新建立连接或重试次数耗尽。
对于如何监测连接是否断开,则是通过重写ChannelInboundHandler#channelInactive来实现,但连接不可用,该方法会被触发,所以只需要在该方法做好重连工作即可。
注:以下代码都是在上面心跳机制的基础上修改/添加的。
因为断线重连是客户端的工作,所以只需对客户端代码进行修改。
public interface RetryPolicy { /** * Called when an operation has failed for some reason. This method should return * true to make another attempt. * * @param retryCount the number of times retried so far (0 the first time) * @return true/false */ boolean allowRetry(int retryCount); /** * get sleep time in ms of current retry count. * * @param retryCount current retry count * @return the time to sleep */ long getSleepTimeMs(int retryCount); }
/** * <p>Retry policy that retries a set number of times with increasing sleep time between retries</p> */ public class ExponentialBackOffRetry implements RetryPolicy { private static final int MAX_RETRIES_LIMIT = 29; private static final int DEFAULT_MAX_SLEEP_MS = Integer.MAX_VALUE; private final Random random = new Random(); private final long baseSleepTimeMs; private final int maxRetries; private final int maxSleepMs; public ExponentialBackOffRetry(int baseSleepTimeMs, int maxRetries) { this(baseSleepTimeMs, maxRetries, DEFAULT_MAX_SLEEP_MS); } public ExponentialBackOffRetry(int baseSleepTimeMs, int maxRetries, int maxSleepMs) { this.maxRetries = maxRetries; this.baseSleepTimeMs = baseSleepTimeMs; this.maxSleepMs = maxSleepMs; } @Override public boolean allowRetry(int retryCount) { if (retryCount < maxRetries) { return true; } return false; } @Override public long getSleepTimeMs(int retryCount) { if (retryCount < 0) { throw new IllegalArgumentException("retries count must greater than 0."); } if (retryCount > MAX_RETRIES_LIMIT) { System.out.println(String.format("maxRetries too large (%d). Pinning to %d", maxRetries, MAX_RETRIES_LIMIT)); retryCount = MAX_RETRIES_LIMIT; } long sleepMs = baseSleepTimeMs * Math.max(1, random.nextInt(1 << retryCount)); if (sleepMs > maxSleepMs) { System.out.println(String.format("Sleep extension too large (%d). Pinning to %d", sleepMs, maxSleepMs)); sleepMs = maxSleepMs; } return sleepMs; } }
@ChannelHandler.Sharable public class ReconnectHandler extends ChannelInboundHandlerAdapter { private int retries = 0; private RetryPolicy retryPolicy; private TcpClient tcpClient; public ReconnectHandler(TcpClient tcpClient) { this.tcpClient = tcpClient; } @Override public void channelActive(ChannelHandlerContext ctx) throws Exception { System.out.println("Successfully established a connection to the server."); retries = 0; ctx.fireChannelActive(); } @Override public void channelInactive(ChannelHandlerContext ctx) throws Exception { if (retries == 0) { System.err.println("Lost the TCP connection with the server."); ctx.close(); } boolean allowRetry = getRetryPolicy().allowRetry(retries); if (allowRetry) { long sleepTimeMs = getRetryPolicy().getSleepTimeMs(retries); System.out.println(String.format("Try to reconnect to the server after %dms. Retry count: %d.", sleepTimeMs, ++retries)); final EventLoop eventLoop = ctx.channel().eventLoop(); eventLoop.schedule(() -> { System.out.println("Reconnecting ..."); tcpClient.connect(); }, sleepTimeMs, TimeUnit.MILLISECONDS); } ctx.fireChannelInactive(); } private RetryPolicy getRetryPolicy() { if (this.retryPolicy == null) { this.retryPolicy = tcpClient.getRetryPolicy(); } return this.retryPolicy; } }
在之前的基础上,添加了重连处理器ReconnectHandler。
public class ClientHandlersInitializer extends ChannelInitializer<SocketChannel> { private ReconnectHandler reconnectHandler; private EchoHandler echoHandler; public ClientHandlersInitializer(TcpClient tcpClient) { Assert.notNull(tcpClient, "TcpClient can not be null."); this.reconnectHandler = new ReconnectHandler(tcpClient); this.echoHandler = new EchoHandler(); } @Override protected void initChannel(SocketChannel ch) throws Exception { ChannelPipeline pipeline = ch.pipeline(); pipeline.addLast(this.reconnectHandler); pipeline.addLast(new LengthFieldBasedFrameDecoder(Integer.MAX_VALUE, 0, 4, 0, 4)); pipeline.addLast(new LengthFieldPrepender(4)); pipeline.addLast(new StringDecoder(CharsetUtil.UTF_8)); pipeline.addLast(new StringEncoder(CharsetUtil.UTF_8)); pipeline.addLast(new Pinger()); } }
在之前的基础上添加重连、重连策略的支持。
public class TcpClient { private String host; private int port; private Bootstrap bootstrap; /** 重连策略 */ private RetryPolicy retryPolicy; /** 将<code>Channel</code>保存起来, 可用于在其他非handler的地方发送数据 */ private Channel channel; public TcpClient(String host, int port) { this(host, port, new ExponentialBackOffRetry(1000, Integer.MAX_VALUE, 60 * 1000)); } public TcpClient(String host, int port, RetryPolicy retryPolicy) { this.host = host; this.port = port; this.retryPolicy = retryPolicy; init(); } /** * 向远程TCP服务器请求连接 */ public void connect() { synchronized (bootstrap) { ChannelFuture future = bootstrap.connect(host, port); future.addListener(getConnectionListener()); this.channel = future.channel(); } } public RetryPolicy getRetryPolicy() { return retryPolicy; } private void init() { EventLoopGroup group = new NioEventLoopGroup(); // bootstrap 可重用, 只需在TcpClient实例化的时候初始化即可. bootstrap = new Bootstrap(); bootstrap.group(group) .channel(NioSocketChannel.class) .handler(new ClientHandlersInitializer(TcpClient.this)); } private ChannelFutureListener getConnectionListener() { return new ChannelFutureListener() { @Override public void operationComplete(ChannelFuture future) throws Exception { if (!future.isSuccess()) { future.channel().pipeline().fireChannelInactive(); } } }; } public static void main(String[] args) { TcpClient tcpClient = new TcpClient("localhost", 2222); tcpClient.connect(); } }
在测试之前,为了避开 Connection reset by peer 异常,可以稍微修改Pinger的ping()方法,添加if (second == 5)的条件判断。如下:
private void ping(Channel channel) { int second = Math.max(1, random.nextInt(baseRandom)); if (second == 5) { second = 6; } System.out.println("next heart beat will send after " + second + "s."); ScheduledFuture<?> future = channel.eventLoop().schedule(new Runnable() { @Override public void run() { if (channel.isActive()) { System.out.println("sending heart beat to the server..."); channel.writeAndFlush(ClientIdleStateTrigger.HEART_BEAT); } else { System.err.println("The connection had broken, cancel the task that will send a heart beat."); channel.closeFuture(); throw new RuntimeException(); } } }, second, TimeUnit.SECONDS); future.addListener(new GenericFutureListener() { @Override public void operationComplete(Future future) throws Exception { if (future.isSuccess()) { ping(channel); } } }); }
先只启动客户端,观察控制台输出,可以看到类似如下日志:
断线重连测试——客户端控制台输出
可以看到,当客户端发现无法连接到服务器端,所以一直尝试重连。随着重试次数增加,重试时间间隔越大,但又不想无限增大下去,所以需要定一个阈值,比如60s。如上图所示,当下一次重试时间超过60s时,会打印Sleep extension too large(*). Pinning to 60000,单位为ms。出现这句话的意思是,计算出来的时间超过阈值(60s),所以把真正睡眠的时间重置为阈值(60s)。
接着启动服务器端,然后继续观察客户端控制台输出。
断线重连测试——服务器端启动后客户端控制台输出
可以看到,在第9次重试失败后,第10次重试之前,启动的服务器,所以第10次重连的结果为Successfully established a connection to the server.,即成功连接到服务器。接下来因为还是不定时ping服务器,所以出现断线重连、断线重连的循环。
在不同环境,可能会有不同的重连需求。有不同的重连需求的,只需自己实现RetryPolicy接口,然后在创建TcpClient的时候覆盖默认的重连策略即可。
完!!!
1. Java JVM、集合、多线程、新特性系列教程
2. Spring MVC、Spring Boot、Spring Cloud 系列教程
3. Maven、Git、Eclipse、Intellij IDEA 系列工具教程
4. Java、后端、架构、阿里巴巴等大厂最新面试题
觉得不错,别忘了点赞+转发哦!