RocketMQ源码分析之Broker注册（1）

在broker启动时会开始第一次注册，以后会定时向注册中心注册本机的信息

this.registerBrokerAll(true, false, true);

    this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {

        @Override
        public void run() {
            try {
                BrokerController.this.registerBrokerAll(true, false, brokerConfig.isForceRegister());
            } catch (Throwable e) {
                log.error("registerBrokerAll Exception", e);
            }
        }
    }, 1000 * 10, Math.max(10000, Math.min(brokerConfig.getRegisterNameServerPeriod(), 60000)), TimeUnit.MILLISECONDS);

包装topic的配置信息以及对应的版本号TopicConfigSerializeWrapper，然后根据本机的读写配置重写topic配置。

public synchronized void registerBrokerAll(final boolean checkOrderConfig, boolean oneway, boolean forceRegister) {
    TopicConfigSerializeWrapper topicConfigWrapper = this.getTopicConfigManager().buildTopicConfigSerializeWrapper();

    if (!PermName.isWriteable(this.getBrokerConfig().getBrokerPermission())
        || !PermName.isReadable(this.getBrokerConfig().getBrokerPermission())) {
        ConcurrentHashMap<String, TopicConfig> topicConfigTable = new ConcurrentHashMap<String, TopicConfig>();
        for (TopicConfig topicConfig : topicConfigWrapper.getTopicConfigTable().values()) {
            TopicConfig tmp =
                new TopicConfig(topicConfig.getTopicName(), topicConfig.getReadQueueNums(), topicConfig.getWriteQueueNums(),
                    this.brokerConfig.getBrokerPermission());
            topicConfigTable.put(topicConfig.getTopicName(), tmp);
        }
        topicConfigWrapper.setTopicConfigTable(topicConfigTable);
    }

    if (forceRegister || needRegister(this.brokerConfig.getBrokerClusterName(),
        this.getBrokerAddr(),
        this.brokerConfig.getBrokerName(),
        this.brokerConfig.getBrokerId(),
        this.brokerConfig.getRegisterBrokerTimeoutMills())) {
        doRegisterBrokerAll(checkOrderConfig, oneway, topicConfigWrapper);
    }
}

当直接注册标识打开时forceRegister直接进行注册，这里我们看一下另一个是否需要注册的条件，超时时间为6000ms，直接开始执行是否注册请求处理

private boolean needRegister(final String clusterName,
    final String brokerAddr,
    final String brokerName,
    final long brokerId,
    final int timeoutMills) {

    TopicConfigSerializeWrapper topicConfigWrapper = this.getTopicConfigManager().buildTopicConfigSerializeWrapper();
    List<Boolean> changeList = brokerOuterAPI.needRegister(clusterName, brokerAddr, brokerName, brokerId, topicConfigWrapper, timeoutMills);
    boolean needRegister = false;
    for (Boolean changed : changeList) {
        if (changed) {
            needRegister = true;
            break;
        }
    }
    return needRegister;
}

先获取配置的所有注册中心的地址，每个地址都需要访问一下，保持一致，当任何一个注册中心返回需要注册的话，那么上面那个请求就会返回true，也就是要给每个注册中心重新注册。这里用CountDownLatch来达到等待所有请求都返回才会执行返回操作，当然对每个注册中心的注册请求都是异步线程进行操作

public List<Boolean> needRegister(
    final String clusterName,
    final String brokerAddr,
    final String brokerName,
    final long brokerId,
    final TopicConfigSerializeWrapper topicConfigWrapper,
    final int timeoutMills) {
    final List<Boolean> changedList = new CopyOnWriteArrayList<>();
    List<String> nameServerAddressList = this.remotingClient.getNameServerAddressList();
    if (nameServerAddressList != null && nameServerAddressList.size() > 0) {
        final CountDownLatch countDownLatch = new CountDownLatch(nameServerAddressList.size());
        for (final String namesrvAddr : nameServerAddressList) {
            brokerOuterExecutor.execute(new Runnable() {
                @Override
                public void run() {
                    try {
                        QueryDataVersionRequestHeader requestHeader = new QueryDataVersionRequestHeader();
                        requestHeader.setBrokerAddr(brokerAddr);
                        requestHeader.setBrokerId(brokerId);
                        requestHeader.setBrokerName(brokerName);
                        requestHeader.setClusterName(clusterName);
                        RemotingCommand request = RemotingCommand.createRequestCommand(RequestCode.QUERY_DATA_VERSION, requestHeader);
                        request.setBody(topicConfigWrapper.getDataVersion().encode());
                        RemotingCommand response = remotingClient.invokeSync(namesrvAddr, request, timeoutMills);
                        DataVersion nameServerDataVersion = null;
                        Boolean changed = false;
                        switch (response.getCode()) {
                            case ResponseCode.SUCCESS: {
                                QueryDataVersionResponseHeader queryDataVersionResponseHeader =
                                    (QueryDataVersionResponseHeader) response.decodeCommandCustomHeader(QueryDataVersionResponseHeader.class);
                                changed = queryDataVersionResponseHeader.getChanged();
                                byte[] body = response.getBody();
                                if (body != null) {
                                    nameServerDataVersion = DataVersion.decode(body, DataVersion.class);
                                    if (!topicConfigWrapper.getDataVersion().equals(nameServerDataVersion)) {
                                        changed = true;
                                    }
                                }
                                if (changed == null || changed) {
                                    changedList.add(Boolean.TRUE);
                                }
                            }
                            default:
                                break;
                        }
                        log.warn("Query data version from name server {} OK,changed {}, broker {},name server {}", namesrvAddr, changed, topicConfigWrapper.getDataVersion(), nameServerDataVersion == null ? "" : nameServerDataVersion);
                    } catch (Exception e) {
                        changedList.add(Boolean.TRUE);
                        log.error("Query data version from name server {}  Exception, {}", namesrvAddr, e);
                    } finally {
                        countDownLatch.countDown();
                    }
                }
            });

        }
        try {
            countDownLatch.await(timeoutMills, TimeUnit.MILLISECONDS);
        } catch (InterruptedException e) {
            log.error("query dataversion from nameserver countDownLatch await Exception", e);
        }
    }
    return changedList;
}

执行线程为

private BrokerFixedThreadPoolExecutor brokerOuterExecutor = new BrokerFixedThreadPoolExecutor(4, 10, 1, TimeUnit.MINUTES,
        new ArrayBlockingQueue<Runnable>(32), new ThreadFactoryImpl("brokerOutApi_thread_", true));

构造请求头QueryDataVersionRequestHeader，code为QUERY_DATA_VERSION = 322;每一种请求都对应一个请求头类以及一个返回类，当然也和请求码code相对应。通过通信客户端执行同步请求操作

public RemotingCommand invokeSync(String addr, final RemotingCommand request, long timeoutMillis)
    throws InterruptedException, RemotingConnectException, RemotingSendRequestException, RemotingTimeoutException {
    long beginStartTime = System.currentTimeMillis();
    final Channel channel = this.getAndCreateChannel(addr);
    if (channel != null && channel.isActive()) {
        try {
            doBeforeRpcHooks(addr, request);
            long costTime = System.currentTimeMillis() - beginStartTime;
            if (timeoutMillis < costTime) {
                throw new RemotingTimeoutException("invokeSync call timeout");
            }
            RemotingCommand response = this.invokeSyncImpl(channel, request, timeoutMillis - costTime);
            doAfterRpcHooks(RemotingHelper.parseChannelRemoteAddr(channel), request, response);
            return response;
        } catch (RemotingSendRequestException e) {
            log.warn("invokeSync: send request exception, so close the channel[{}]", addr);
            this.closeChannel(addr, channel);
            throw e;
        } catch (RemotingTimeoutException e) {
            if (nettyClientConfig.isClientCloseSocketIfTimeout()) {
                this.closeChannel(addr, channel);
                log.warn("invokeSync: close socket because of timeout, {}ms, {}", timeoutMillis, addr);
            }
            log.warn("invokeSync: wait response timeout exception, the channel[{}]", addr);
            throw e;
        }
    } else {
        this.closeChannel(addr, channel);
        throw new RemotingConnectException(addr);
    }
}

获取通信通道，如果没有的话就直接创建，最后保存起来

 private Channel getAndCreateChannel(final String addr) throws InterruptedException {
    if (null == addr) {
        return getAndCreateNameserverChannel();
    }

    ChannelWrapper cw = this.channelTables.get(addr);
    if (cw != null && cw.isOK()) {
        return cw.getChannel();
    }

    return this.createChannel(addr);
}

当不传递对应的配置中心地址时，就会选择一个地址创建通信通道

private Channel getAndCreateNameserverChannel() throws InterruptedException {
    String addr = this.namesrvAddrChoosed.get();
    if (addr != null) {
        ChannelWrapper cw = this.channelTables.get(addr);
        if (cw != null && cw.isOK()) {
            return cw.getChannel();
        }
    }

    final List<String> addrList = this.namesrvAddrList.get();
    if (this.lockNamesrvChannel.tryLock(LOCK_TIMEOUT_MILLIS, TimeUnit.MILLISECONDS)) {
        try {
            addr = this.namesrvAddrChoosed.get();
            if (addr != null) {
                ChannelWrapper cw = this.channelTables.get(addr);
                if (cw != null && cw.isOK()) {
                    return cw.getChannel();
                }
            }

            if (addrList != null && !addrList.isEmpty()) {
                for (int i = 0; i < addrList.size(); i++) {
                    int index = this.namesrvIndex.incrementAndGet();
                    index = Math.abs(index);
                    index = index % addrList.size();
                    String newAddr = addrList.get(index);

                    this.namesrvAddrChoosed.set(newAddr);
                    log.info("new name server is chosen. OLD: {} , NEW: {}. namesrvIndex = {}", addr, newAddr, namesrvIndex);
                    Channel channelNew = this.createChannel(newAddr);
                    if (channelNew != null) {
                        return channelNew;
                    }
                }
            }
        } catch (Exception e) {
            log.error("getAndCreateNameserverChannel: create name server channel exception", e);
        } finally {
            this.lockNamesrvChannel.unlock();
        }
    } else {
        log.warn("getAndCreateNameserverChannel: try to lock name server, but timeout, {}ms", LOCK_TIMEOUT_MILLIS);
    }

    return null;
}

创建一个新的通讯通道，然后和配置中心进行连接返回ChannelFuture包装成ChannelWrapper保存起来后等待连接成功，超时时间为3000ms。成功后返回

private Channel createChannel(final String addr) throws InterruptedException {
    ChannelWrapper cw = this.channelTables.get(addr);
    if (cw != null && cw.isOK()) {
        cw.getChannel().close();
        channelTables.remove(addr);
    }

    if (this.lockChannelTables.tryLock(LOCK_TIMEOUT_MILLIS, TimeUnit.MILLISECONDS)) {
        try {
            boolean createNewConnection;
            cw = this.channelTables.get(addr);
            if (cw != null) {

                if (cw.isOK()) {
                    cw.getChannel().close();
                    this.channelTables.remove(addr);
                    createNewConnection = true;
                } else if (!cw.getChannelFuture().isDone()) {
                    createNewConnection = false;
                } else {
                    this.channelTables.remove(addr);
                    createNewConnection = true;
                }
            } else {
                createNewConnection = true;
            }

            if (createNewConnection) {
                ChannelFuture channelFuture = this.bootstrap.connect(RemotingHelper.string2SocketAddress(addr));
                log.info("createChannel: begin to connect remote host[{}] asynchronously", addr);
                cw = new ChannelWrapper(channelFuture);
                this.channelTables.put(addr, cw);
            }
        } catch (Exception e) {
            log.error("createChannel: create channel exception", e);
        } finally {
            this.lockChannelTables.unlock();
        }
    } else {
        log.warn("createChannel: try to lock channel table, but timeout, {}ms", LOCK_TIMEOUT_MILLIS);
    }

    if (cw != null) {
        ChannelFuture channelFuture = cw.getChannelFuture();
        if (channelFuture.awaitUninterruptibly(this.nettyClientConfig.getConnectTimeoutMillis())) {
            if (cw.isOK()) {
                log.info("createChannel: connect remote host[{}] success, {}", addr, channelFuture.toString());
                return cw.getChannel();
            } else {
                log.warn("createChannel: connect remote host[" + addr + "] failed, " + channelFuture.toString(), channelFuture.cause());
            }
        } else {
            log.warn("createChannel: connect remote host[{}] timeout {}ms, {}", addr, this.nettyClientConfig.getConnectTimeoutMillis(),
                channelFuture.toString());
        }
    }

    return null;
}

判断通信通道是否有效后执行rpc请求前置钩子，完事后判断是否已经超时

protected void doBeforeRpcHooks(String addr, RemotingCommand request) {
    if (rpcHooks.size() > 0) {
        for (RPCHook rpcHook: rpcHooks) {
            rpcHook.doBeforeRequest(addr, request);
        }
    }
}

执行同步请求，请求命令在创建时会创建该次请求id即opaque，把对应的信息包装成ResponseFuture与对应的请求id存储起来，等待后续失败或者成功后移除。通道监听器主要是看请求有没有发送成功，当成功后就会设置对应的状态后返回，不成功则设置状态后清除掉前面保存的请求设置返回为null

public RemotingCommand invokeSyncImpl(final Channel channel, final RemotingCommand request,
    final long timeoutMillis)
    throws InterruptedException, RemotingSendRequestException, RemotingTimeoutException {
    final int opaque = request.getOpaque();

    try {
        final ResponseFuture responseFuture = new ResponseFuture(channel, opaque, timeoutMillis, null, null);
        this.responseTable.put(opaque, responseFuture);
        final SocketAddress addr = channel.remoteAddress();
        channel.writeAndFlush(request).addListener(new ChannelFutureListener() {
            @Override
            public void operationComplete(ChannelFuture f) throws Exception {
                if (f.isSuccess()) {
                    responseFuture.setSendRequestOK(true);
                    return;
                } else {
                    responseFuture.setSendRequestOK(false);
                }

                responseTable.remove(opaque);
                responseFuture.setCause(f.cause());
                responseFuture.putResponse(null);
                log.warn("send a request command to channel <" + addr + "> failed.");
            }
        });

        RemotingCommand responseCommand = responseFuture.waitResponse(timeoutMillis);
        if (null == responseCommand) {
            if (responseFuture.isSendRequestOK()) {
                throw new RemotingTimeoutException(RemotingHelper.parseSocketAddressAddr(addr), timeoutMillis,
                    responseFuture.getCause());
            } else {
                throw new RemotingSendRequestException(RemotingHelper.parseSocketAddressAddr(addr), responseFuture.getCause());
            }
        }

        return responseCommand;
    } finally {
        this.responseTable.remove(opaque);
    }
}

后面的程序一直在等待对应的相应，当写入失败的时候会唤醒，或者是超时时间到达，再就是正确的回应到达时会唤醒该操作，最后判断回应后返回。

public RemotingCommand waitResponse(final long timeoutMillis) throws InterruptedException {
    this.countDownLatch.await(timeoutMillis, TimeUnit.MILLISECONDS);
    return this.responseCommand;
}
 public void putResponse(final RemotingCommand responseCommand) {
    this.responseCommand = responseCommand;
    this.countDownLatch.countDown();
}