系列
开篇
- 这篇文章的主要目的是分析RocketMq Broker的线程模型和快速失败机制。
- 线程模型的核心是按照不同的业务通过不同的线程池进行处理。
- 快速失败机制是针对线程池中任务堆积的情况快速失败然后由业务侧重试。
线程模型分析
public class BrokerController {
private final ScheduledExecutorService scheduledExecutorService = Executors.newSingleThreadScheduledExecutor(new ThreadFactoryImpl(
"BrokerControllerScheduledThread"));
// broker侧各类业务线程池等待的队列
private final BlockingQueue<Runnable> sendThreadPoolQueue;
private final BlockingQueue<Runnable> pullThreadPoolQueue;
private final BlockingQueue<Runnable> replyThreadPoolQueue;
private final BlockingQueue<Runnable> queryThreadPoolQueue;
private final BlockingQueue<Runnable> clientManagerThreadPoolQueue;
private final BlockingQueue<Runnable> heartbeatThreadPoolQueue;
private final BlockingQueue<Runnable> consumerManagerThreadPoolQueue;
private final BlockingQueue<Runnable> endTransactionThreadPoolQueue;
// broker侧各类业务对应的ExecutorService
private ExecutorService sendMessageExecutor;
private ExecutorService pullMessageExecutor;
private ExecutorService replyMessageExecutor;
private ExecutorService queryMessageExecutor;
private ExecutorService adminBrokerExecutor;
private ExecutorService clientManageExecutor;
private ExecutorService heartbeatExecutor;
private ExecutorService consumerManageExecutor;
private ExecutorService endTransactionExecutor;
private BrokerFastFailure brokerFastFailure;
public BrokerController(
final BrokerConfig brokerConfig,
final NettyServerConfig nettyServerConfig,
final NettyClientConfig nettyClientConfig,
final MessageStoreConfig messageStoreConfig
) {
// 负责创建各类线程池队列
// private int sendThreadPoolQueueCapacity = 10000;
// private int pullThreadPoolQueueCapacity = 100000;
// private int replyThreadPoolQueueCapacity = 10000;
// private int queryThreadPoolQueueCapacity = 20000;
// private int clientManagerThreadPoolQueueCapacity = 1000000;
// private int consumerManagerThreadPoolQueueCapacity = 1000000;
// private int heartbeatThreadPoolQueueCapacity = 50000;
// private int endTransactionPoolQueueCapacity = 100000;
this.sendThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getSendThreadPoolQueueCapacity());
this.pullThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getPullThreadPoolQueueCapacity());
this.replyThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getReplyThreadPoolQueueCapacity());
this.queryThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getQueryThreadPoolQueueCapacity());
this.clientManagerThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getClientManagerThreadPoolQueueCapacity());
this.consumerManagerThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getConsumerManagerThreadPoolQueueCapacity());
this.heartbeatThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getHeartbeatThreadPoolQueueCapacity());
this.endTransactionThreadPoolQueue = new LinkedBlockingQueue<Runnable>(this.brokerConfig.getEndTransactionPoolQueueCapacity());
// 快速失败检测服务
this.brokerFastFailure = new BrokerFastFailure(this);
}
public boolean initialize() throws CloneNotSupportedException {
if (result) {
// 创建各类ThreadPoolExecutor并绑定对应的Queue
this.sendMessageExecutor = new BrokerFixedThreadPoolExecutor(
this.brokerConfig.getSendMessageThreadPoolNums(),
this.brokerConfig.getSendMessageThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.sendThreadPoolQueue,
new ThreadFactoryImpl("SendMessageThread_"));
this.pullMessageExecutor = new BrokerFixedThreadPoolExecutor(
this.brokerConfig.getPullMessageThreadPoolNums(),
this.brokerConfig.getPullMessageThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.pullThreadPoolQueue,
new ThreadFactoryImpl("PullMessageThread_"));
this.replyMessageExecutor = new BrokerFixedThreadPoolExecutor(
this.brokerConfig.getProcessReplyMessageThreadPoolNums(),
this.brokerConfig.getProcessReplyMessageThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.replyThreadPoolQueue,
new ThreadFactoryImpl("ProcessReplyMessageThread_"));
this.queryMessageExecutor = new BrokerFixedThreadPoolExecutor(
this.brokerConfig.getQueryMessageThreadPoolNums(),
this.brokerConfig.getQueryMessageThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.queryThreadPoolQueue,
new ThreadFactoryImpl("QueryMessageThread_"));
this.adminBrokerExecutor =
Executors.newFixedThreadPool(this.brokerConfig.getAdminBrokerThreadPoolNums(), new ThreadFactoryImpl(
"AdminBrokerThread_"));
this.clientManageExecutor = new ThreadPoolExecutor(
this.brokerConfig.getClientManageThreadPoolNums(),
this.brokerConfig.getClientManageThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.clientManagerThreadPoolQueue,
new ThreadFactoryImpl("ClientManageThread_"));
this.heartbeatExecutor = new BrokerFixedThreadPoolExecutor(
this.brokerConfig.getHeartbeatThreadPoolNums(),
this.brokerConfig.getHeartbeatThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.heartbeatThreadPoolQueue,
new ThreadFactoryImpl("HeartbeatThread_", true));
this.endTransactionExecutor = new BrokerFixedThreadPoolExecutor(
this.brokerConfig.getEndTransactionThreadPoolNums(),
this.brokerConfig.getEndTransactionThreadPoolNums(),
1000 * 60,
TimeUnit.MILLISECONDS,
this.endTransactionThreadPoolQueue,
new ThreadFactoryImpl("EndTransactionThread_"));
this.consumerManageExecutor =
Executors.newFixedThreadPool(this.brokerConfig.getConsumerManageThreadPoolNums(), new ThreadFactoryImpl(
"ConsumerManageThread_"));
// 注册各类处理Processor
this.registerProcessor();
}
}
public void registerProcessor() {
/**
* SendMessageProcessor
*/
SendMessageProcessor sendProcessor = new SendMessageProcessor(this);
sendProcessor.registerSendMessageHook(sendMessageHookList);
sendProcessor.registerConsumeMessageHook(consumeMessageHookList);
// 绑定请求编码、Processor、ThreadPoolExecutor之间的关系
this.remotingServer.registerProcessor(RequestCode.SEND_MESSAGE, sendProcessor, this.sendMessageExecutor);
this.remotingServer.registerProcessor(RequestCode.SEND_MESSAGE_V2, sendProcessor, this.sendMessageExecutor);
this.remotingServer.registerProcessor(RequestCode.SEND_BATCH_MESSAGE, sendProcessor, this.sendMessageExecutor);
this.remotingServer.registerProcessor(RequestCode.CONSUMER_SEND_MSG_BACK, sendProcessor, this.sendMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.SEND_MESSAGE, sendProcessor, this.sendMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.SEND_MESSAGE_V2, sendProcessor, this.sendMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.SEND_BATCH_MESSAGE, sendProcessor, this.sendMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.CONSUMER_SEND_MSG_BACK, sendProcessor, this.sendMessageExecutor);
this.remotingServer.registerProcessor(RequestCode.PULL_MESSAGE, this.pullMessageProcessor, this.pullMessageExecutor);
this.pullMessageProcessor.registerConsumeMessageHook(consumeMessageHookList);
ReplyMessageProcessor replyMessageProcessor = new ReplyMessageProcessor(this);
replyMessageProcessor.registerSendMessageHook(sendMessageHookList);
this.remotingServer.registerProcessor(RequestCode.SEND_REPLY_MESSAGE, replyMessageProcessor, replyMessageExecutor);
this.remotingServer.registerProcessor(RequestCode.SEND_REPLY_MESSAGE_V2, replyMessageProcessor, replyMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.SEND_REPLY_MESSAGE, replyMessageProcessor, replyMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.SEND_REPLY_MESSAGE_V2, replyMessageProcessor, replyMessageExecutor);
/**
* QueryMessageProcessor
*/
NettyRequestProcessor queryProcessor = new QueryMessageProcessor(this);
this.remotingServer.registerProcessor(RequestCode.QUERY_MESSAGE, queryProcessor, this.queryMessageExecutor);
this.remotingServer.registerProcessor(RequestCode.VIEW_MESSAGE_BY_ID, queryProcessor, this.queryMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.QUERY_MESSAGE, queryProcessor, this.queryMessageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.VIEW_MESSAGE_BY_ID, queryProcessor, this.queryMessageExecutor);
/**
* ClientManageProcessor
*/
ClientManageProcessor clientProcessor = new ClientManageProcessor(this);
this.remotingServer.registerProcessor(RequestCode.HEART_BEAT, clientProcessor, this.heartbeatExecutor);
this.remotingServer.registerProcessor(RequestCode.UNREGISTER_CLIENT, clientProcessor, this.clientManageExecutor);
this.remotingServer.registerProcessor(RequestCode.CHECK_CLIENT_CONFIG, clientProcessor, this.clientManageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.HEART_BEAT, clientProcessor, this.heartbeatExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.UNREGISTER_CLIENT, clientProcessor, this.clientManageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.CHECK_CLIENT_CONFIG, clientProcessor, this.clientManageExecutor);
/**
* ConsumerManageProcessor
*/
ConsumerManageProcessor consumerManageProcessor = new ConsumerManageProcessor(this);
this.remotingServer.registerProcessor(RequestCode.GET_CONSUMER_LIST_BY_GROUP, consumerManageProcessor, this.consumerManageExecutor);
this.remotingServer.registerProcessor(RequestCode.UPDATE_CONSUMER_OFFSET, consumerManageProcessor, this.consumerManageExecutor);
this.remotingServer.registerProcessor(RequestCode.QUERY_CONSUMER_OFFSET, consumerManageProcessor, this.consumerManageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.GET_CONSUMER_LIST_BY_GROUP, consumerManageProcessor, this.consumerManageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.UPDATE_CONSUMER_OFFSET, consumerManageProcessor, this.consumerManageExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.QUERY_CONSUMER_OFFSET, consumerManageProcessor, this.consumerManageExecutor);
/**
* EndTransactionProcessor
*/
this.remotingServer.registerProcessor(RequestCode.END_TRANSACTION, new EndTransactionProcessor(this), this.endTransactionExecutor);
this.fastRemotingServer.registerProcessor(RequestCode.END_TRANSACTION, new EndTransactionProcessor(this), this.endTransactionExecutor);
/**
* Default
*/
AdminBrokerProcessor adminProcessor = new AdminBrokerProcessor(this);
this.remotingServer.registerDefaultProcessor(adminProcessor, this.adminBrokerExecutor);
this.fastRemotingServer.registerDefaultProcessor(adminProcessor, this.adminBrokerExecutor);
}
}
- BrokerController内部根据不同的服务创建不同的ThreadPoolQueue，如sendThreadPoolQueue、pullThreadPoolQueue等。
- BrokerController内部根据不同的服务创建不同的ExecutorService，如sendMessageExecutor、pullMessageExecutor等。
- BrokerController内部根据不同的服务创建不同的Processor，如SendMessageProcessor、replyMessageProcessor等。
- BrokerController通过registerProcessor()方法来实现请求编码、Processor、ExecutorService的绑定。
- 根据绑定关系可知，每个请求编码会由对应的ExecutorService去执行对应的Processor来完成功能。
- BrokerFastFailure负责检测并实现快速失败的功能。
public class BrokerFixedThreadPoolExecutor extends ThreadPoolExecutor {
public BrokerFixedThreadPoolExecutor(final int corePoolSize, final int maximumPoolSize, final long keepAliveTime,
final TimeUnit unit,
final BlockingQueue<Runnable> workQueue, final ThreadFactory threadFactory) {
super(corePoolSize, maximumPoolSize, keepAliveTime, unit, workQueue, threadFactory);
}
protected <T> RunnableFuture<T> newTaskFor(final Runnable runnable, final T value) {
return new FutureTaskExt<T>(runnable, value);
}
}
- 重写了newTaskFor，在submit中将RequestTask包装成FutureTaskExt对象进行处理。
public class NettyRemotingServer extends NettyRemotingAbstract implements RemotingServer {
public void registerProcessor(int requestCode, NettyRequestProcessor processor, ExecutorService executor) {
ExecutorService executorThis = executor;
if (null == executor) {
executorThis = this.publicExecutor;
}
Pair<NettyRequestProcessor, ExecutorService> pair = new Pair<NettyRequestProcessor, ExecutorService>(processor, executorThis);
this.processorTable.put(requestCode, pair);
}
}
public abstract class NettyRemotingAbstract {
protected final HashMap<Integer/* request code */, Pair<NettyRequestProcessor, ExecutorService>> processorTable =
new HashMap<Integer, Pair<NettyRequestProcessor, ExecutorService>>(64);
}
- registerProcessor实现Processor和ExecutorService的Pair对，并绑定对应的请求码。
消息处理流程
public class NettyRemotingServer extends NettyRemotingAbstract implements RemotingServer {
public void start() {
this.defaultEventExecutorGroup = new DefaultEventExecutorGroup(
nettyServerConfig.getServerWorkerThreads(),
new ThreadFactory() {
private AtomicInteger threadIndex = new AtomicInteger(0);
@Override
public Thread newThread(Runnable r) {
return new Thread(r, "NettyServerCodecThread_" + this.threadIndex.incrementAndGet());
}
});
prepareSharableHandlers();
ServerBootstrap childHandler =
this.serverBootstrap.group(this.eventLoopGroupBoss, this.eventLoopGroupSelector)
.channel(useEpoll() ? EpollServerSocketChannel.class : NioServerSocketChannel.class)
.option(ChannelOption.SO_BACKLOG, 1024)
.option(ChannelOption.SO_REUSEADDR, true)
.option(ChannelOption.SO_KEEPALIVE, false)
.childOption(ChannelOption.TCP_NODELAY, true)
.childOption(ChannelOption.SO_SNDBUF, nettyServerConfig.getServerSocketSndBufSize())
.childOption(ChannelOption.SO_RCVBUF, nettyServerConfig.getServerSocketRcvBufSize())
.localAddress(new InetSocketAddress(this.nettyServerConfig.getListenPort()))
.childHandler(new ChannelInitializer<SocketChannel>() {
@Override
public void initChannel(SocketChannel ch) throws Exception {
ch.pipeline()
.addLast(defaultEventExecutorGroup, HANDSHAKE_HANDLER_NAME, handshakeHandler)
.addLast(defaultEventExecutorGroup,
encoder,
new NettyDecoder(),
new IdleStateHandler(0, 0, nettyServerConfig.getServerChannelMaxIdleTimeSeconds()),
connectionManageHandler,
serverHandler
);
}
});
try {
ChannelFuture sync = this.serverBootstrap.bind().sync();
InetSocketAddress addr = (InetSocketAddress) sync.channel().localAddress();
this.port = addr.getPort();
} catch (InterruptedException e1) {
throw new RuntimeException("this.serverBootstrap.bind().sync() InterruptedException", e1);
}
}
private void prepareSharableHandlers() {
handshakeHandler = new HandshakeHandler(TlsSystemConfig.tlsMode);
encoder = new NettyEncoder();
connectionManageHandler = new NettyConnectManageHandler();
serverHandler = new NettyServerHandler();
}
class NettyServerHandler extends SimpleChannelInboundHandler<RemotingCommand> {
@Override
protected void channelRead0(ChannelHandlerContext ctx, RemotingCommand msg) throws Exception {
processMessageReceived(ctx, msg);
}
}
}
- NettyRemotingServer在启动的过程中绑定serverHandler，是NettyServerHandler对象。
- NettyServerHandler处理消息读事件channelRead0的过程中执行processMessageReceived来处理消息事件。
public abstract class NettyRemotingAbstract {
public void processMessageReceived(ChannelHandlerContext ctx, RemotingCommand msg) throws Exception {
final RemotingCommand cmd = msg;
if (cmd != null) {
switch (cmd.getType()) {
case REQUEST_COMMAND:
processRequestCommand(ctx, cmd);
break;
case RESPONSE_COMMAND:
processResponseCommand(ctx, cmd);
break;
default:
break;
}
}
}
public void processRequestCommand(final ChannelHandlerContext ctx, final RemotingCommand cmd) {
final Pair<NettyRequestProcessor, ExecutorService> matched = this.processorTable.get(cmd.getCode());
final Pair<NettyRequestProcessor, ExecutorService> pair = null == matched ? this.defaultRequestProcessor : matched;
final int opaque = cmd.getOpaque();
if (pair != null) {
Runnable run = new Runnable() {
@Override
public void run() {
try {
doBeforeRpcHooks(RemotingHelper.parseChannelRemoteAddr(ctx.channel()), cmd);
final RemotingCommand response = pair.getObject1().processRequest(ctx, cmd);
doAfterRpcHooks(RemotingHelper.parseChannelRemoteAddr(ctx.channel()), cmd, response);
if (!cmd.isOnewayRPC()) {
if (response != null) {
response.setOpaque(opaque);
response.markResponseType();
try {
ctx.writeAndFlush(response);
} catch (Throwable e) {
log.error("process request over, but response failed", e);
log.error(cmd.toString());
log.error(response.toString());
}
} else {
}
}
} catch (Throwable e) {
}
}
};
try {
final RequestTask requestTask = new RequestTask(run, ctx.channel(), cmd);
pair.getObject2().submit(requestTask);
} catch (RejectedExecutionException e) {
}
} else {
String error = " request type " + cmd.getCode() + " not supported";
final RemotingCommand response =
RemotingCommand.createResponseCommand(RemotingSysResponseCode.REQUEST_CODE_NOT_SUPPORTED, error);
response.setOpaque(opaque);
ctx.writeAndFlush(response);
log.error(RemotingHelper.parseChannelRemoteAddr(ctx.channel()) + error);
}
}
}
- processRequestCommand根据请求码RemotingCommand的code找对应的Pair对，包含对应的Processor和ExecutorService。
- 将cmd封装成对应的RequestTask，并通过pair.getObject2().submit(requestTask)由ExecutorService来执行对应的Task。
-
消息处理的核心是通过ExecutorService来处理cmd对应的RequestTask。
BrokerFastFailure快速失败
public class BrokerFastFailure {
private static final InternalLogger log = InternalLoggerFactory.getLogger(LoggerName.BROKER_LOGGER_NAME);
private final ScheduledExecutorService scheduledExecutorService = Executors.newSingleThreadScheduledExecutor(new ThreadFactoryImpl(
"BrokerFastFailureScheduledThread"));
private final BrokerController brokerController;
public BrokerFastFailure(final BrokerController brokerController) {
this.brokerController = brokerController;
}
public void start() {
this.scheduledExecutorService.scheduleAtFixedRate(new Runnable() {
@Override
public void run() {
if (brokerController.getBrokerConfig().isBrokerFastFailureEnable()) {
cleanExpiredRequest();
}
}
}, 1000, 10, TimeUnit.MILLISECONDS);
}
}
- BrokerFastFailure每10ms执行清除过期请求，核心方法cleanExpiredRequest。
public class BrokerFastFailure {
private void cleanExpiredRequest() {
while (this.brokerController.getMessageStore().isOSPageCacheBusy()) {
try {
if (!this.brokerController.getSendThreadPoolQueue().isEmpty()) {
final Runnable runnable = this.brokerController.getSendThreadPoolQueue().poll(0, TimeUnit.SECONDS);
if (null == runnable) {
break;
}
final RequestTask rt = castRunnable(runnable);
rt.returnResponse(RemotingSysResponseCode.SYSTEM_BUSY, String.format("[PCBUSY_CLEAN_QUEUE]broker busy, start flow control for a while, period in queue: %sms, size of queue: %d", System.currentTimeMillis() - rt.getCreateTimestamp(), this.brokerController.getSendThreadPoolQueue().size()));
} else {
break;
}
} catch (Throwable ignored) {
}
}
cleanExpiredRequestInQueue(this.brokerController.getSendThreadPoolQueue(),
this.brokerController.getBrokerConfig().getWaitTimeMillsInSendQueue());
cleanExpiredRequestInQueue(this.brokerController.getPullThreadPoolQueue(),
this.brokerController.getBrokerConfig().getWaitTimeMillsInPullQueue());
cleanExpiredRequestInQueue(this.brokerController.getHeartbeatThreadPoolQueue(),
this.brokerController.getBrokerConfig().getWaitTimeMillsInHeartbeatQueue());
cleanExpiredRequestInQueue(this.brokerController.getEndTransactionThreadPoolQueue(), this
.brokerController.getBrokerConfig().getWaitTimeMillsInTransactionQueue());
}
}
- 负责定时清理SendThreadPoolQueue、PullThreadPoolQueue、HeartbeatThreadPoolQueue、EndTransactionThreadPoolQueue。
public class BrokerFastFailure {
public static RequestTask castRunnable(final Runnable runnable) {
try {
if (runnable instanceof FutureTaskExt) {
FutureTaskExt object = (FutureTaskExt) runnable;
return (RequestTask) object.getRunnable();
}
} catch (Throwable e) {
log.error(String.format("castRunnable exception, %s", runnable.getClass().getName()), e);
}
return null;
}
void cleanExpiredRequestInQueue(final BlockingQueue<Runnable> blockingQueue, final long maxWaitTimeMillsInQueue) {
while (true) {
try {
if (!blockingQueue.isEmpty()) {
// Retrieves, but does not remove, the head of this queue
final Runnable runnable = blockingQueue.peek();
if (null == runnable) {
break;
}
final RequestTask rt = castRunnable(runnable);
if (rt == null || rt.isStopRun()) {
break;
}
// 检查超时是否超过maxWaitTimeMillsInQueue
// private long waitTimeMillsInSendQueue = 200;
// private long waitTimeMillsInPullQueue = 5 * 1000;
// private long waitTimeMillsInHeartbeatQueue = 31 * 1000;
// private long waitTimeMillsInTransactionQueue = 3 * 1000;
final long behind = System.currentTimeMillis() - rt.getCreateTimestamp();
if (behind >= maxWaitTimeMillsInQueue) {
if (blockingQueue.remove(runnable)) {
rt.setStopRun(true);
rt.returnResponse(RemotingSysResponseCode.SYSTEM_BUSY, String.format("[TIMEOUT_CLEAN_QUEUE]broker busy, start flow control for a while, period in queue: %sms, size of queue: %d", behind, blockingQueue.size()));
}
} else {
break;
}
} else {
break;
}
} catch (Throwable ignored) {
}
}
}
}
- 获取任务队列中的第一个元素并判断是否超时，如果超时则立即返回错误码SYSTEM_BUSY。
网友评论