public void registerProcessor() {
/**
* SendMessageProcessor
*/
SendMessageProcessor sendProcessor = new SendMessageProcessor(this);
sendProcessor.registerSendMessageHook(sendMessageHookList);
sendProcessor.registerConsumeMessageHook(consumeMessageHookList);
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);
它注册了SendMessageProcessor来处理从producer客户端发来的SEND_MESSAGE消息。我们从netty客户端这边看起。在nettyRemotingServer的start方法中,给netty的serverBoostrup中添加了NettyServerHandler,其重写了channelRead0方法,即netty客户端消息发送来的时候,服务端在这里接收到并处理。
class NettyServerHandler extends SimpleChannelInboundHandler<RemotingCommand> {
@Override
protected void channelRead0(ChannelHandlerContext ctx, RemotingCommand msg) throws Exception {
processMessageReceived(ctx, msg);
}
}
我们来看下processMessageRecived方法
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;
}
}
}
由于生产者客户端传入的请求,因此其cmd的type自然是REQUEST_CMMAND,调用processRequestCommond()
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 {
RPCHook rpcHook = NettyRemotingAbstract.this.getRPCHook();
if (rpcHook != null) {
rpcHook.doBeforeRequest(RemotingHelper.parseChannelRemoteAddr(ctx.channel()), cmd);
}
final RemotingCommand response = pair.getObject1().processRequest(ctx, cmd);
if (rpcHook != null) {
rpcHook.doAfterResponse(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) {
log.error("process request exception", e);
log.error(cmd.toString());
if (!cmd.isOnewayRPC()) {
final RemotingCommand response = RemotingCommand.createResponseCommand(RemotingSysResponseCode.SYSTEM_ERROR,
RemotingHelper.exceptionSimpleDesc(e));
response.setOpaque(opaque);
ctx.writeAndFlush(response);
}
}
}
};
if (pair.getObject1().rejectRequest()) {
final RemotingCommand response = RemotingCommand.createResponseCommand(RemotingSysResponseCode.SYSTEM_BUSY,
"[REJECTREQUEST]system busy, start flow control for a while");
response.setOpaque(opaque);
ctx.writeAndFlush(response);
return;
}
try {
final RequestTask requestTask = new RequestTask(run, ctx.channel(), cmd);
pair.getObject2().submit(requestTask);
} catch (RejectedExecutionException e) {
if ((System.currentTimeMillis() % 10000) == 0) {
log.warn(RemotingHelper.parseChannelRemoteAddr(ctx.channel())
+ ", too many requests and system thread pool busy, RejectedExecutionException "
+ pair.getObject2().toString()
+ " request code: " + cmd.getCode());
}
if (!cmd.isOnewayRPC()) {
final RemotingCommand response = RemotingCommand.createResponseCommand(RemotingSysResponseCode.SYSTEM_BUSY,
"[OVERLOAD]system busy, start flow control for a while");
response.setOpaque(opaque);
ctx.writeAndFlush(response);
}
}
} 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);
}
}
其中具体调用processRequest方法处理来的消息,得到response,并通过netty中ctx的writeAndFlush将处理结果发回至生产者客户端。processRequest的具体逻辑在sendMessageProcessor中
@Override
public RemotingCommand processRequest(ChannelHandlerContext ctx,
RemotingCommand request) throws RemotingCommandException {
SendMessageContext mqtraceContext;
switch (request.getCode()) {
case RequestCode.CONSUMER_SEND_MSG_BACK:
return this.consumerSendMsgBack(ctx, request);
default:
SendMessageRequestHeader requestHeader = parseRequestHeader(request);
if (requestHeader == null) {
return null;
}
mqtraceContext = buildMsgContext(ctx, requestHeader);
this.executeSendMessageHookBefore(ctx, request, mqtraceContext);
RemotingCommand response;
if (requestHeader.isBatch()) {
response = this.sendBatchMessage(ctx, request, mqtraceContext, requestHeader);
} else {
response = this.sendMessage(ctx, request, mqtraceContext, requestHeader);
}
this.executeSendMessageHookAfter(response, mqtraceContext);
return response;
}
}
很自然的注意到sendMessage()方法,Broker接收得到的来自provider的消息的具体处理就从这开始介绍。
private RemotingCommand sendMessage(final ChannelHandlerContext ctx,
final RemotingCommand request,
final SendMessageContext sendMessageContext,
final SendMessageRequestHeader requestHeader) throws RemotingCommandException {
final RemotingCommand response = RemotingCommand.createResponseCommand(SendMessageResponseHeader.class);
final SendMessageResponseHeader responseHeader = (SendMessageResponseHeader) response.readCustomHeader();
response.setOpaque(request.getOpaque());
response.addExtField(MessageConst.PROPERTY_MSG_REGION, this.brokerController.getBrokerConfig().getRegionId());
response.addExtField(MessageConst.PROPERTY_TRACE_SWITCH, String.valueOf(this.brokerController.getBrokerConfig().isTraceOn()));
log.debug("receive SendMessage request command, {}", request);
final long startTimstamp = this.brokerController.getBrokerConfig().getStartAcceptSendRequestTimeStamp();
if (this.brokerController.getMessageStore().now() < startTimstamp) {
response.setCode(ResponseCode.SYSTEM_ERROR);
response.setRemark(String.format("broker unable to service, until %s", UtilAll.timeMillisToHumanString2(startTimstamp)));
return response;
}
response.setCode(-1);
super.msgCheck(ctx, requestHeader, response);
if (response.getCode() != -1) {
return response;
}
final byte[] body = request.getBody();
int queueIdInt = requestHeader.getQueueId();
TopicConfig topicConfig = this.brokerController.getTopicConfigManager().selectTopicConfig(requestHeader.getTopic());
if (queueIdInt < 0) {
queueIdInt = Math.abs(this.random.nextInt() % 99999999) % topicConfig.getWriteQueueNums();
}
MessageExtBrokerInner msgInner = new MessageExtBrokerInner();
msgInner.setTopic(requestHeader.getTopic());
msgInner.setQueueId(queueIdInt);
if (!handleRetryAndDLQ(requestHeader, response, request, msgInner, topicConfig)) {
return response;
}
msgInner.setBody(body);
msgInner.setFlag(requestHeader.getFlag());
MessageAccessor.setProperties(msgInner, MessageDecoder.string2messageProperties(requestHeader.getProperties()));
msgInner.setPropertiesString(requestHeader.getProperties());
msgInner.setBornTimestamp(requestHeader.getBornTimestamp());
msgInner.setBornHost(ctx.channel().remoteAddress());
msgInner.setStoreHost(this.getStoreHost());
msgInner.setReconsumeTimes(requestHeader.getReconsumeTimes() == null ? 0 : requestHeader.getReconsumeTimes());
if (this.brokerController.getBrokerConfig().isRejectTransactionMessage()) {
String traFlag = msgInner.getProperty(MessageConst.PROPERTY_TRANSACTION_PREPARED);
if (traFlag != null) {
response.setCode(ResponseCode.NO_PERMISSION);
response.setRemark(
"the broker[" + this.brokerController.getBrokerConfig().getBrokerIP1() + "] sending transaction message
is forbidden");
return response;
}
}
PutMessageResult putMessageResult = this.brokerController.getMessageStore().putMessage(msgInner);
return handlePutMessageResult(putMessageResult, response, request, msgInner, responseHeader, sendMessageContext
, ctx, queueIdInt);
}
先构造response以及responseHeader,根据request的信息配置好response,并且根据break的存储时间看其消息是否是延迟收到,是的话则不处理,设为error返回。将接收到的消息封装为MessageExtBrokerInner。然后将其通过messageStore的putMessage方法将收到的消息传递至存储层处理,在这里将存储结果PutMessageResult等参数通过handlerPutMessageResult()处理。
这里的messageStore采用的默认DefaultMessageStore
public PutMessageResult putMessage(MessageExtBrokerInner msg) {
if (this.shutdown) {
log.warn("message store has shutdown, so putMessage is forbidden");
return new PutMessageResult(PutMessageStatus.SERVICE_NOT_AVAILABLE, null);
}
if (BrokerRole.SLAVE == this.messageStoreConfig.getBrokerRole()) {
long value = this.printTimes.getAndIncrement();
if ((value % 50000) == 0) {
log.warn("message store is slave mode, so putMessage is forbidden ");
}
return new PutMessageResult(PutMessageStatus.SERVICE_NOT_AVAILABLE, null);
}
if (!this.runningFlags.isWriteable()) {
long value = this.printTimes.getAndIncrement();
if ((value % 50000) == 0) {
log.warn("message store is not writeable, so putMessage is forbidden " + this.runningFlags.getFlagBits());
}
return new PutMessageResult(PutMessageStatus.SERVICE_NOT_AVAILABLE, null);
} else {
this.printTimes.set(0);
}
if (msg.getTopic().length() > Byte.MAX_VALUE) {
log.warn("putMessage message topic length too long " + msg.getTopic().length());
return new PutMessageResult(PutMessageStatus.MESSAGE_ILLEGAL, null);
}
if (msg.getPropertiesString() != null && msg.getPropertiesString().length() > Short.MAX_VALUE) {
log.warn("putMessage message properties length too long " + msg.getPropertiesString().length());
return new PutMessageResult(PutMessageStatus.PROPERTIES_SIZE_EXCEEDED, null);
}
if (this.isOSPageCacheBusy()) {
return new PutMessageResult(PutMessageStatus.OS_PAGECACHE_BUSY, null);
}
long beginTime = this.getSystemClock().now();
PutMessageResult result = this.commitLog.putMessage(msg);
long eclipseTime = this.getSystemClock().now() - beginTime;
if (eclipseTime > 500) {
log.warn("putMessage not in lock eclipse time(ms)={}, bodyLength={}", eclipseTime, msg.getBody().length);
}
this.storeStatsService.setPutMessageEntireTimeMax(eclipseTime);
if (null == result || !result.isOk()) {
this.storeStatsService.getPutMessageFailedTimes().incrementAndGet();
}
return result;
}
这里先检测操作系统写入是否忙,通过调用commitLog的putMessage()方法来存储消息,并记录该方法的耗时eclipseTime设置到storeStatesServeice中,如果失败,则storeStatesServeice的失败次数加一。
我们来看下commitLog的putMessage()方法
public PutMessageResult putMessage(final MessageExtBrokerInner msg) {
// Set the storage time
msg.setStoreTimestamp(System.currentTimeMillis());
// Set the message body BODY CRC (consider the most appropriate setting
// on the client)
msg.setBodyCRC(UtilAll.crc32(msg.getBody()));
// Back to Results
AppendMessageResult result = null;
StoreStatsService storeStatsService = this.defaultMessageStore.getStoreStatsService();
String topic = msg.getTopic();
int queueId = msg.getQueueId();
final int tranType = MessageSysFlag.getTransactionValue(msg.getSysFlag());
if (tranType == MessageSysFlag.TRANSACTION_NOT_TYPE
|| tranType == MessageSysFlag.TRANSACTION_COMMIT_TYPE) {
// Delay Delivery
if (msg.getDelayTimeLevel() > 0) {
if (msg.getDelayTimeLevel() > this.defaultMessageStore.getScheduleMessageService().getMaxDelayLevel()) {
msg.setDelayTimeLevel(this.defaultMessageStore.getScheduleMessageService().getMaxDelayLevel());
}
topic = ScheduleMessageService.SCHEDULE_TOPIC;
queueId = ScheduleMessageService.delayLevel2QueueId(msg.getDelayTimeLevel());
// Backup real topic, queueId
MessageAccessor.putProperty(msg, MessageConst.PROPERTY_REAL_TOPIC, msg.getTopic());
MessageAccessor.putProperty(msg, MessageConst.PROPERTY_REAL_QUEUE_ID, String.valueOf(msg.getQueueId()));
msg.setPropertiesString(MessageDecoder.messageProperties2String(msg.getProperties()));
msg.setTopic(topic);
msg.setQueueId(queueId);
}
}
long eclipseTimeInLock = 0;
MappedFile unlockMappedFile = null;
MappedFile mappedFile = this.mappedFileQueue.getLastMappedFile();
putMessageLock.lock(); //spin or ReentrantLock ,depending on store config
try {
long beginLockTimestamp = this.defaultMessageStore.getSystemClock().now();
this.beginTimeInLock = beginLockTimestamp;
// Here settings are stored timestamp, in order to ensure an orderly
// global
msg.setStoreTimestamp(beginLockTimestamp);
if (null == mappedFile || mappedFile.isFull()) {
mappedFile = this.mappedFileQueue.getLastMappedFile(0); // Mark: NewFile may be cause noise
}
if (null == mappedFile) {
log.error("create mapped file1 error, topic: " + msg.getTopic() + " clientAddr: " + msg.getBornHostString());
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.CREATE_MAPEDFILE_FAILED, null);
}
result = mappedFile.appendMessage(msg, this.appendMessageCallback);
switch (result.getStatus()) {
case PUT_OK:
break;
case END_OF_FILE:
unlockMappedFile = mappedFile;
// Create a new file, re-write the message
mappedFile = this.mappedFileQueue.getLastMappedFile(0);
if (null == mappedFile) {
// XXX: warn and notify me
log.error("create mapped file2 error, topic: " + msg.getTopic() + " clientAddr: " + msg.getBornHostString());
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.CREATE_MAPEDFILE_FAILED, result);
}
result = mappedFile.appendMessage(msg, this.appendMessageCallback);
break;
case MESSAGE_SIZE_EXCEEDED:
case PROPERTIES_SIZE_EXCEEDED:
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.MESSAGE_ILLEGAL, result);
case UNKNOWN_ERROR:
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.UNKNOWN_ERROR, result);
default:
beginTimeInLock = 0;
return new PutMessageResult(PutMessageStatus.UNKNOWN_ERROR, result);
}
eclipseTimeInLock = this.defaultMessageStore.getSystemClock().now() - beginLockTimestamp;
beginTimeInLock = 0;
} finally {
putMessageLock.unlock();
}
if (eclipseTimeInLock > 500) {
log.warn("[NOTIFYME]putMessage in lock cost time(ms)={}, bodyLength={} AppendMessageResult={}"
, eclipseTimeInLock, msg.getBody().length, result);
}
if (null != unlockMappedFile && this.defaultMessageStore.getMessageStoreConfig().isWarmMapedFileEnable()) {
this.defaultMessageStore.unlockMappedFile(unlockMappedFile);
}
PutMessageResult putMessageResult = new PutMessageResult(PutMessageStatus.PUT_OK, result);
// Statistics
storeStatsService.getSinglePutMessageTopicTimesTotal(msg.getTopic()).incrementAndGet();
storeStatsService.getSinglePutMessageTopicSizeTotal(topic).addAndGet(result.getWroteBytes());
handleDiskFlush(result, putMessageResult, msg);
handleHA(result, putMessageResult, msg);
return putMessageResult;
}
从接收到的消息中的sysFlag得到消息的类型(事务、非事务、提交Commit类型),如果是非事务、提交类型则配置延迟交货。
需要提一下,broker在存储消息的方式中采用MappedFileQueue方式,将不连续的物理文件抽象成一串连续的逻辑文件来处理。MapedFile管理具体的物理文件的映射。所有消息队列的消息的存储均共用这里的MappedFileQueue抽象的连续文件进行消息的存储,用各自的各个消息的偏移量offset在这里取出具体的数据。
固定一个MappedFile的大小为MappedFileSize,那么偏移量offset的消息存于(offset-fileFromOffset)/MappedFileSize为下标的MappedFile中的低offset%fileFromOffset字节开始。
那么存数据,无非找到最后的MappedFile,再加锁,并设置beginLockTimestamp时间戳,如果此时发现取得的最后一个MappedFile为null或者满了,那么重新创建一个。
然后调用mappedFile的anppendMessage并传入要存储的消息跟appendMessageCallback,通过MappedFile对象写入文件,得到AppendMessageResult。
最后根据AppendMessageResult的结果来判断消息写入文件的情况,此时可能消息过长MappedFile剩余的部分不够写,重新申请一个mappedFile并调用其anppendMessage。
然后计算处理的总时间,解锁。最后根据刷盘策略刷盘、主从同步。
appendMessage()方法直接调用了appendMessagesInner()
public AppendMessageResult appendMessagesInner(final MessageExt messageExt, final AppendMessageCallback cb) {
assert messageExt != null;
assert cb != null;
int currentPos = this.wrotePosition.get();
if (currentPos < this.fileSize) {
ByteBuffer byteBuffer = writeBuffer != null ? writeBuffer.slice() : this.mappedByteBuffer.slice();
byteBuffer.position(currentPos);
AppendMessageResult result = null;
if (messageExt instanceof MessageExtBrokerInner) {
result = cb.doAppend(this.getFileFromOffset(), byteBuffer, this.fileSize - currentPos,
(MessageExtBrokerInner) messageExt);
} else if (messageExt instanceof MessageExtBatch) {
result = cb.doAppend(this.getFileFromOffset(), byteBuffer, this.fileSize - currentPos, (MessageExtBatch) messageExt);
} else {
return new AppendMessageResult(AppendMessageStatus.UNKNOWN_ERROR);
}
this.wrotePosition.addAndGet(result.getWroteBytes());
this.storeTimestamp = result.getStoreTimestamp();
return result;
}
log.error("MappedFile.appendMessage return null, wrotePosition: {} fileSize: {}", currentPos, this.fileSize);
return new AppendMessageResult(AppendMessageStatus.UNKNOWN_ERROR);
}
我们可以看到这里逻辑并不复杂,其调用了callBack的doAppend方法,其实现实在传入的DefaultAppendMessageCallback中
public AppendMessageResult doAppend(final long fileFromOffset, final ByteBuffer byteBuffer, final int maxBlank,
final MessageExtBrokerInner msgInner) {
// STORETIMESTAMP + STOREHOSTADDRESS + OFFSET <br>
// PHY OFFSET
long wroteOffset = fileFromOffset + byteBuffer.position();
this.resetByteBuffer(hostHolder, 8);
String msgId = MessageDecoder.createMessageId(this.msgIdMemory, msgInner.getStoreHostBytes(hostHolder), wroteOffset);
// Record ConsumeQueue information
keyBuilder.setLength(0);
keyBuilder.append(msgInner.getTopic());
keyBuilder.append('-');
keyBuilder.append(msgInner.getQueueId());
String key = keyBuilder.toString();
Long queueOffset = CommitLog.this.topicQueueTable.get(key);
if (null == queueOffset) {
queueOffset = 0L;
CommitLog.this.topicQueueTable.put(key, queueOffset);
}
// Transaction messages that require special handling
final int tranType = MessageSysFlag.getTransactionValue(msgInner.getSysFlag());
switch (tranType) {
// Prepared and Rollback message is not consumed, will not enter the
// consumer queuec
case MessageSysFlag.TRANSACTION_PREPARED_TYPE:
case MessageSysFlag.TRANSACTION_ROLLBACK_TYPE:
queueOffset = 0L;
break;
case MessageSysFlag.TRANSACTION_NOT_TYPE:
case MessageSysFlag.TRANSACTION_COMMIT_TYPE:
default:
break;
}
/**
* Serialize message
*/
final byte[] propertiesData =
msgInner.getPropertiesString() == null ? null : msgInner.getPropertiesString().getBytes(MessageDecoder.CHARSET_UTF8);
final int propertiesLength = propertiesData == null ? 0 : propertiesData.length;
if (propertiesLength > Short.MAX_VALUE) {
log.warn("putMessage message properties length too long. length={}", propertiesData.length);
return new AppendMessageResult(AppendMessageStatus.PROPERTIES_SIZE_EXCEEDED);
}
final byte[] topicData = msgInner.getTopic().getBytes(MessageDecoder.CHARSET_UTF8);
final int topicLength = topicData.length;
final int bodyLength = msgInner.getBody() == null ? 0 : msgInner.getBody().length;
final int msgLen = calMsgLength(bodyLength, topicLength, propertiesLength);
// Exceeds the maximum message
if (msgLen > this.maxMessageSize) {
CommitLog.log.warn("message size exceeded, msg total size: " + msgLen + ", msg body size: " + bodyLength
+ ", maxMessageSize: " + this.maxMessageSize);
return new AppendMessageResult(AppendMessageStatus.MESSAGE_SIZE_EXCEEDED);
}
// Determines whether there is sufficient free space
if ((msgLen + END_FILE_MIN_BLANK_LENGTH) > maxBlank) {
this.resetByteBuffer(this.msgStoreItemMemory, maxBlank);
// 1 TOTALSIZE
this.msgStoreItemMemory.putInt(maxBlank);
// 2 MAGICCODE
this.msgStoreItemMemory.putInt(CommitLog.BLANK_MAGIC_CODE);
// 3 The remaining space may be any value
// Here the length of the specially set maxBlank
final long beginTimeMills = CommitLog.this.defaultMessageStore.now();
byteBuffer.put(this.msgStoreItemMemory.array(), 0, maxBlank);
return new AppendMessageResult(AppendMessageStatus.END_OF_FILE, wroteOffset, maxBlank, msgId,
msgInner.getStoreTimestamp(), queueOffset, CommitLog.this.defaultMessageStore.now() - beginTimeMills);
}
// Initialization of storage space
this.resetByteBuffer(msgStoreItemMemory, msgLen);
// 1 TOTALSIZE
this.msgStoreItemMemory.putInt(msgLen);
// 2 MAGICCODE
this.msgStoreItemMemory.putInt(CommitLog.MESSAGE_MAGIC_CODE);
// 3 BODYCRC
this.msgStoreItemMemory.putInt(msgInner.getBodyCRC());
// 4 QUEUEID
this.msgStoreItemMemory.putInt(msgInner.getQueueId());
// 5 FLAG
this.msgStoreItemMemory.putInt(msgInner.getFlag());
// 6 QUEUEOFFSET
this.msgStoreItemMemory.putLong(queueOffset);
// 7 PHYSICALOFFSET
this.msgStoreItemMemory.putLong(fileFromOffset + byteBuffer.position());
// 8 SYSFLAG
this.msgStoreItemMemory.putInt(msgInner.getSysFlag());
// 9 BORNTIMESTAMP
this.msgStoreItemMemory.putLong(msgInner.getBornTimestamp());
// 10 BORNHOST
this.resetByteBuffer(hostHolder, 8);
this.msgStoreItemMemory.put(msgInner.getBornHostBytes(hostHolder));
// 11 STORETIMESTAMP
this.msgStoreItemMemory.putLong(msgInner.getStoreTimestamp());
// 12 STOREHOSTADDRESS
this.resetByteBuffer(hostHolder, 8);
this.msgStoreItemMemory.put(msgInner.getStoreHostBytes(hostHolder));
//this.msgBatchMemory.put(msgInner.getStoreHostBytes());
// 13 RECONSUMETIMES
this.msgStoreItemMemory.putInt(msgInner.getReconsumeTimes());
// 14 Prepared Transaction Offset
this.msgStoreItemMemory.putLong(msgInner.getPreparedTransactionOffset());
// 15 BODY
this.msgStoreItemMemory.putInt(bodyLength);
if (bodyLength > 0)
this.msgStoreItemMemory.put(msgInner.getBody());
// 16 TOPIC
this.msgStoreItemMemory.put((byte) topicLength);
this.msgStoreItemMemory.put(topicData);
// 17 PROPERTIES
this.msgStoreItemMemory.putShort((short) propertiesLength);
if (propertiesLength > 0)
this.msgStoreItemMemory.put(propertiesData);
final long beginTimeMills = CommitLog.this.defaultMessageStore.now();
// Write messages to the queue buffer
byteBuffer.put(this.msgStoreItemMemory.array(), 0, msgLen);
AppendMessageResult result = new AppendMessageResult(AppendMessageStatus.PUT_OK, wroteOffset, msgLen, msgId,
msgInner.getStoreTimestamp(), queueOffset, CommitLog.this.defaultMessageStore.now() - beginTimeMills);
switch (tranType) {
case MessageSysFlag.TRANSACTION_PREPARED_TYPE:
case MessageSysFlag.TRANSACTION_ROLLBACK_TYPE:
break;
case MessageSysFlag.TRANSACTION_NOT_TYPE:
case MessageSysFlag.TRANSACTION_COMMIT_TYPE:
// The next update ConsumeQueue information
CommitLog.this.topicQueueTable.put(key, ++queueOffset);
break;
default:
break;
}
return result;
}
先计算出已经写了的偏移量wroteOffset
构造msgId,msgId的格式4byte的ip+4byte的port+8byte的wroteOffset
然后构造key,key的格式: topic-消息队列Id,然后根据key从topicQueueTable中查找指定topic指定消息队列下的偏移量,如果找不到,那默认为0,并以键值对形式加入topicQueueTable中。
判断消息的类型,进行不同的处理。当然消息的长度不能大于maxMessageSize。
按照一定的格式,将接收到的消息写到byteBuffer即(writenBuffer)中。
然后构造AppendMessageResult
public AppendMessageResult(AppendMessageStatus status, long wroteOffset, int wroteBytes, String msgId,
long storeTimestamp, long logicsOffset, long pagecacheRT) {
this.status = status;
this.wroteOffset = wroteOffset;
this.wroteBytes = wroteBytes;
this.msgId = msgId;
this.storeTimestamp = storeTimestamp;
this.logicsOffset = logicsOffset;
this.pagecacheRT = pagecacheRT;
}
追加消息结果status、消息的偏移量wroteOffset(相对于整个commitlog)、消息待写入字节wroteBytes、消息ID msgI、消息写入时间戳storeTimestamp、消息队列偏移量queueOffset、pagecacheRT。
返回到mappedFile的appendMessageInner方法中,当把消息封装到mappedFile的writeBuffer中后,更新writePosition跟storeTimestamp后返回。
返回到CommitLog的putMessage中,退出同步。进行消息刷写,我们来看下handleDiskFlush方法
public void handleDiskFlush(AppendMessageResult result, PutMessageResult putMessageResult, MessageExt messageExt) {
// Synchronization flush
if (FlushDiskType.SYNC_FLUSH == this.defaultMessageStore.getMessageStoreConfig().getFlushDiskType()) {
final GroupCommitService service = (GroupCommitService) this.flushCommitLogService;
if (messageExt.isWaitStoreMsgOK()) {
GroupCommitRequest request = new GroupCommitRequest(result.getWroteOffset() + result.getWroteBytes());
service.putRequest(request);
boolean flushOK = request.waitForFlush(this.defaultMessageStore.getMessageStoreConfig().getSyncFlushTimeout());
if (!flushOK) {
log.error("do groupcommit, wait for flush failed, topic: " + messageExt.getTopic() + " tags: " + messageExt.getTags()
+ " client address: " + messageExt.getBornHostString());
putMessageResult.setPutMessageStatus(PutMessageStatus.FLUSH_DISK_TIMEOUT);
}
} else {
service.wakeup();
}
}
// Asynchronous flush
else {
if (!this.defaultMessageStore.getMessageStoreConfig().isTransientStorePoolEnable()) {
flushCommitLogService.wakeup();
} else {
commitLogService.wakeup();
}
}
}
分为同步跟异步两种方式,我们先来看下同步的方式。
同步方式下有两种配置,一种是收到等待消息存储ok的消息才返回,默认为true。进去条件分支后,我们看到其构造了GroupCommitRequest,并调用其waitForFlush方法。
public boolean waitForFlush(long timeout) {
try {
this.countDownLatch.await(timeout, TimeUnit.MILLISECONDS);
return this.flushOK;
} catch (InterruptedException e) {
log.error("Interrupted", e);
return false;
}
}
可以看到这个方法后,主线程停在了同步屏障上,等待其他线程cutDown。由于DefaultMessageStore的启动,CommitLog的start方法即在其启动的时候已经调用
public void start() {
this.flushCommitLogService.start();
if (defaultMessageStore.getMessageStoreConfig().isTransientStorePoolEnable()) {
this.commitLogService.start();
}
}
我们先来看下flushCommitLogService的run方法,即GroupCommitService的run方法
public void run() {
CommitLog.log.info(this.getServiceName() + " service started");
while (!this.isStopped()) {
try {
this.waitForRunning(10);
this.doCommit();
} catch (Exception e) {
CommitLog.log.warn(this.getServiceName() + " service has exception. ", e);
}
}
// Under normal circumstances shutdown, wait for the arrival of the
// request, and then flush
try {
Thread.sleep(10);
} catch (InterruptedException e) {
CommitLog.log.warn("GroupCommitService Exception, ", e);
}
synchronized (this) {
this.swapRequests();
}
this.doCommit();
CommitLog.log.info(this.getServiceName() + " service end");
}
可以看到,后台有一个线程不停的执行doCommit方法,然后等待10毫秒,我们看下doCommit方法。
private void doCommit() {
synchronized (this.requestsRead) {
if (!this.requestsRead.isEmpty()) {
for (GroupCommitRequest req : this.requestsRead) {
// There may be a message in the next file, so a maximum of
// two times the flush
boolean flushOK = false;
for (int i = 0; i < 2 && !flushOK; i++) {
flushOK = CommitLog.this.mappedFileQueue.getFlushedWhere() >= req.getNextOffset();
if (!flushOK) {
CommitLog.this.mappedFileQueue.flush(0);
}
}
req.wakeupCustomer(flushOK);
}
long storeTimestamp = CommitLog.this.mappedFileQueue.getStoreTimestamp();
if (storeTimestamp > 0) {
CommitLog.this.defaultMessageStore.getStoreCheckpoint().setPhysicMsgTimestamp(storeTimestamp);
}
this.requestsRead.clear();
} else {
// Because of individual messages is set to not sync flush, it
// will come to this process
CommitLog.this.mappedFileQueue.flush(0);
}
}
}
我们可以看到调用mappedFileQueue.flush方法将数据进行向文件中冲刷。对于每条消息这儿起了两次循环,可以理解到万一有一条消息一部分处于一个文件尾,一部分处于另一个文件头,于是需要两次冲刷,但一条消息最多需要两次,大部分都是一次。
冲刷完毕后,调用req.wakeupCustomer方法,让在同步屏障等待的线程冲过同步屏障,因为此时消息冲刷已经完成。
我们看下mappedFileQueue的flush方法
public boolean flush(final int flushLeastPages) {
boolean result = true;
MappedFile mappedFile = this.findMappedFileByOffset(this.flushedWhere, this.flushedWhere == 0);
if (mappedFile != null) {
long tmpTimeStamp = mappedFile.getStoreTimestamp();
int offset = mappedFile.flush(flushLeastPages);
long where = mappedFile.getFileFromOffset() + offset;
result = where == this.flushedWhere;
this.flushedWhere = where;
if (0 == flushLeastPages) {
this.storeTimestamp = tmpTimeStamp;
}
}
return result;
}
通过每个消息的offset得到具体的mappedFile,调用mappedFile的flush完成刷盘,剩下无非是offset的计算,跟时间戳。我们继续跟下去。
public int flush(final int flushLeastPages) {
if (this.isAbleToFlush(flushLeastPages)) {
if (this.hold()) {
int value = getReadPosition();
try {
//We only append data to fileChannel or mappedByteBuffer, never both.
if (writeBuffer != null || this.fileChannel.position() != 0) {
this.fileChannel.force(false);
} else {
this.mappedByteBuffer.force();
}
} catch (Throwable e) {
log.error("Error occurred when force data to disk.", e);
}
this.flushedPosition.set(value);
this.release();
} else {
log.warn("in flush, hold failed, flush offset = " + this.flushedPosition.get());
this.flushedPosition.set(getReadPosition());
}
}
return this.getFlushedPosition();
}
到这里我们就可以看到通过调用fileChannel的force方法冲刷消息。但此时又有疑问了,我们把消息写到了writeBuffer中,什么时候writerBuffer中的消息跑到了fileChannel中,仅通过fileChannel的force方法即可强制将其写入文件磁盘中?我们忽略了另一个serveice的run方法。
此时看到CommitLog的start方法,如果我们采用了TransientStorePool,即使用writeBuffer,那么启动commitLogService,我们看其run方法
@Override
public void run() {
CommitLog.log.info(this.getServiceName() + " service started");
while (!this.isStopped()) {
int interval = CommitLog.this.defaultMessageStore.getMessageStoreConfig().getCommitIntervalCommitLog();
int commitDataLeastPages = CommitLog.this.defaultMessageStore.getMessageStoreConfig().getCommitCommitLogLeastPages();
int commitDataThoroughInterval =
CommitLog.this.defaultMessageStore.getMessageStoreConfig().getCommitCommitLogThoroughInterval();
long begin = System.currentTimeMillis();
if (begin >= (this.lastCommitTimestamp + commitDataThoroughInterval)) {
this.lastCommitTimestamp = begin;
commitDataLeastPages = 0;
}
try {
boolean result = CommitLog.this.mappedFileQueue.commit(commitDataLeastPages);
long end = System.currentTimeMillis();
if (!result) {
this.lastCommitTimestamp = end; // result = false means some data committed.
//now wake up flush thread.
flushCommitLogService.wakeup();
}
if (end - begin > 500) {
log.info("Commit data to file costs {} ms", end - begin);
}
this.waitForRunning(interval);
} catch (Throwable e) {
CommitLog.log.error(this.getServiceName() + " service has exception. ", e);
}
}
boolean result = false;
for (int i = 0; i < RETRY_TIMES_OVER && !result; i++) {
result = CommitLog.this.mappedFileQueue.commit(0);
CommitLog.log.info(this.getServiceName() + " service shutdown, retry " + (i + 1) + " times " +
(result ? "OK" : "Not OK"));
}
CommitLog.log.info(this.getServiceName() + " service end");
}
可以看到其也是调用mappedFileQueue的commit方法,然后调用waitForRunning等待配置的时长,再继续循环。
我们比较关心的是mappedFileQueue的commit方法
public boolean commit(final int commitLeastPages) {
boolean result = true;
MappedFile mappedFile = this.findMappedFileByOffset(this.committedWhere, this.committedWhere == 0);
if (mappedFile != null) {
int offset = mappedFile.commit(commitLeastPages);
long where = mappedFile.getFileFromOffset() + offset;
result = where == this.committedWhere;
this.committedWhere = where;
}
return result;
}
计算偏移量得到mappedFile,再调用mappedFile的commit方法
public int commit(final int commitLeastPages) {
if (writeBuffer == null) {
//no need to commit data to file channel, so just regard wrotePosition as committedPosition.
return this.wrotePosition.get();
}
if (this.isAbleToCommit(commitLeastPages)) {
if (this.hold()) {
commit0(commitLeastPages);
this.release();
} else {
log.warn("in commit, hold failed, commit offset = " + this.committedPosition.get());
}
}
// All dirty data has been committed to FileChannel.
if (writeBuffer != null && this.transientStorePool != null && this.fileSize == this.committedPosition.get()) {
this.transientStorePool.returnBuffer(writeBuffer);
this.writeBuffer = null;
}
return this.committedPosition.get();
}
看到这里相比那个疑惑解决了,在后台有个线程不断的把writeBuffer写到fileChannel中,然后刷盘只要把fileChannel中的数据写入到磁盘中就ok了。
protected void commit0(final int commitLeastPages) {
int writePos = this.wrotePosition.get();
int lastCommittedPosition = this.committedPosition.get();
if (writePos - this.committedPosition.get() > 0) {
try {
ByteBuffer byteBuffer = writeBuffer.slice();
byteBuffer.position(lastCommittedPosition);
byteBuffer.limit(writePos);
this.fileChannel.position(lastCommittedPosition);
this.fileChannel.write(byteBuffer);
this.committedPosition.set(writePos);
} catch (Throwable e) {
log.error("Error occurred when commit data to FileChannel.", e);
}
}
}
其实异步的更简单,直接唤醒commitLogService让其将writeBuffer中的数据写到fileChannel中,再让fileChannel先空闲时候自己写入磁盘,不强制写入。
可以思考下,为什么要开启writeBuffer?刷盘是无需同步的,但是把接收到的消息存到本地内存中的时候是需要在同步块中进行的,因此采用内存字节缓冲区,可提高消息插入的性能。再一步思考,同步刷盘性能应该是低于异步,首先它配置了等结果的话他需要等待,更多的原因是调用fileChannel的force方法强制写入性能会低于,filechannel在其空闲时写入,增加程序整体性能。(由于本人接触的水平有限,思考可能有错,如果有问题望指出)
到这里broker对接收到的消息的存储算是分析完了,接下来调用handleHA进行主从同步。