broker从producer接收消息，然后持久化到本地。consumer再从本地的文件中读取消息，进行消费。rocketmq之所以能够有这么好的性能，与他的这种落盘，然后从磁盘中读取数据的方式有密切的关系。也是rocketmq最值得研读的地方。
1.broker接受到producer发送的信息，准备进行落盘操做SendMessageProcessor#sendMessage
2.校验消息信息，并且同时持久化topic信息，同步nameserver
AbstractSendMessageProcessor#msgCheck
3.如果重试次数大于最大重试次数，就替换为死信队列SendMessageProcessor#handleRetryAndDLQ
4.如果是事务消息，也替换一下topic，然后进行落盘，如果不是事务消息，直接落盘
5.消息存储，获取最后一个mappedFile，然后进行插入，如果发现剩余空间无法插入，则插入blank，并且返回END_OF_FILE，重新再获取一下最后一个mappedFile，CommitLog#putMessages
6.然后再进行插入DefaultAppendMessageCallback#doAppend(long, java.nio.ByteBuffer, int, org.apache.rocketmq.store.MessageExtBrokerInner)
7.刷盘CommitLog#handleDiskFlush，CommitLog.GroupCommitService
8.同步到其他salve，CommitLog#handleHA
因为rocketmq是顺序写的，运用了page cache，所以写的速度接近与内存的直接写。
他的读是随机读的，但是对整体来说又是顺序的，只是一个page cache中随机读。所以也是接近内存的读。
private RemotingCommand sendMessage(final ChannelHandlerContext ctx,
final RemotingCommand request,
final SendMessageContext sendMessageContext,
final SendMessageRequestHeader requestHeader) throws RemotingCommandException {
//构建RemotingCommand 对象
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);
//如果broker开始接受与发送请求的时间比目前消息存储的时间大，就报错
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);
//校验一下消息 里面包含了对broker信息的更新，以及当前broker的topic信息的持久化，以及nameserver的注册
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);
//处理重试超过次数的队列，如果超过了最大的重试次数，就将topic设置为死性队列的topic
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());
PutMessageResult putMessageResult = null;
Map<String, String> oriProps = MessageDecoder.string2messageProperties(requestHeader.getProperties());
String traFlag = oriProps.get(MessageConst.PROPERTY_TRANSACTION_PREPARED);
//如果是事务消息，就替换一下topic信息，然后存入文件
if (traFlag != null && Boolean.parseBoolean(traFlag)) {
if (this.brokerController.getBrokerConfig().isRejectTransactionMessage()) {
response.setCode(ResponseCode.NO_PERMISSION);
response.setRemark(
"the broker[" + this.brokerController.getBrokerConfig().getBrokerIP1()
+ "] sending transaction message is forbidden");
return response;
}
//将数据落盘，设置不同的topic，不让consumer读取
putMessageResult = this.brokerController.getTransactionalMessageService().prepareMessage(msgInner);
} else {
//将数据落盘
putMessageResult = this.brokerController.getMessageStore().putMessage(msgInner);
}
return handlePutMessageResult(putMessageResult, response, request, msgInner, responseHeader, sendMessageContext, ctx, queueIdInt);
}
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);
}
//SLAVE不允许写入
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);
}
//判断一下是不是有写的权限
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);
}
//判断一下topic的名称是不是太长
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();
//将消息写入commitlog中
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;
}
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());
//如果不是事务消息或者是事务提交消息
if (tranType == MessageSysFlag.TRANSACTION_NOT_TYPE
|| tranType == MessageSysFlag.TRANSACTION_COMMIT_TYPE) {
// 如果是延迟投递的，就将topic换掉，并且指定相应的队列名
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;
//获取最后的一个mappedFile
MappedFile mappedFile = this.mappedFileQueue.getLastMappedFile();
//根据配置来决定锁的类型
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);
//如果mappedFile为null或者已经写满了，就创建一个mappedFile
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);
}
//写入mappedFile
result = mappedFile.appendMessage(msg, this.appendMessageCallback);
switch (result.getStatus()) {
case PUT_OK:
break;
case END_OF_FILE:
//如果已经满了，那么将老的mappedFile赋值给unlockMappedFile，然后创建一个mappedFile。再写入
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);
}
//如果unlockMappedFile不为空，并且可以预热文件
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());
//刷盘
handleDiskFlush(result, putMessageResult, msg);
//同步数据
handleHA(result, putMessageResult, msg);
return putMessageResult;
}
public MappedFile getLastMappedFile(final long startOffset, boolean needCreate) {
long createOffset = -1;
MappedFile mappedFileLast = getLastMappedFile();
//如果没有MappedFile的话，就从startOffset开始
if (mappedFileLast == null) {
createOffset = startOffset - (startOffset % this.mappedFileSize);
}
//如果mappedFileLast不为空，并且已经写满了，
if (mappedFileLast != null && mappedFileLast.isFull()) {
createOffset = mappedFileLast.getFileFromOffset() + this.mappedFileSize;
}
if (createOffset != -1 && needCreate) {
//可以知道mapfile的名称为fileName[n - 1] + n * mappedFileSize
String nextFilePath = this.storePath + File.separator + UtilAll.offset2FileName(createOffset);
String nextNextFilePath = this.storePath + File.separator
+ UtilAll.offset2FileName(createOffset + this.mappedFileSize);
MappedFile mappedFile = null;
if (this.allocateMappedFileService != null) {
mappedFile = this.allocateMappedFileService.putRequestAndReturnMappedFile(nextFilePath,
nextNextFilePath, this.mappedFileSize);
} else {
try {
mappedFile = new MappedFile(nextFilePath, this.mappedFileSize);
} catch (IOException e) {
log.error("create mappedFile exception", e);
}
}
if (mappedFile != null) {
if (this.mappedFiles.isEmpty()) {
mappedFile.setFirstCreateInQueue(true);
}
this.mappedFiles.add(mappedFile);
}
return mappedFile;
}
return mappedFileLast;
}
public AppendMessageResult appendMessagesInner(final MessageExt messageExt, final AppendMessageCallback cb) {
assert messageExt != null;
assert cb != null;
//获取当前mapfile的存储位置
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) {
//执行callback的append方法
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);
}
public AppendMessageResult doAppend(final long fileFromOffset, final ByteBuffer byteBuffer, final int maxBlank,
final MessageExtBrokerInner msgInner) {
// STORETIMESTAMP + STOREHOSTADDRESS + OFFSET <br>
//需要写到的offset
long wroteOffset = fileFromOffset + byteBuffer.position();
//获取一下msgId
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();
//根据topic以及对应的队列id获取相应队列的Offset
Long queueOffset = CommitLog.this.topicQueueTable.get(key);
if (null == queueOffset) {
queueOffset = 0L;
CommitLog.this.topicQueueTable.put(key, queueOffset);
}
// 判断一下是不是事务消息
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);
}
// 如果已经没有足够的空间了，就写入blank，然后返回
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);
//以下可以看到commitlog的存储结构是什么
// 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;
}
网友评论