RocketMQ之broker訊息儲存
它註冊了SendMessageProcessor來處理從producer客戶端發來的SEND_MESSAGE訊息。我們從netty客戶端這邊看起。在nettyRemotingServer的start方法中,給netty的serverBoostrup中添加了NettyServerHandler,其重寫了channelRead0方法,即netty客戶端訊息傳送來的時候,服務端在這裡接收到並處理。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);
我們來看下processMessageRecived方法class NettyServerHandler extends SimpleChannelInboundHandler<RemotingCommand> { @Override protected void channelRead0(ChannelHandlerContext ctx, RemotingCommand msg) throws Exception { processMessageReceived(ctx, msg); } }
由於生產者客戶端傳入的請求,因此其cmd的type自然是REQUEST_CMMAND,呼叫processRequestCommond()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 {
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);
}
}
其中具體呼叫processRequest方法處理來的訊息,得到response,並通過netty中ctx的writeAndFlush將處理結果發回至生產者客戶端。processRequest的具體邏輯在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接收得到的來自provider的訊息的具體處理就從這開始介紹。 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);
}
先構造response以及responseHeader,根據request的資訊配置好response,並且根據break的儲存時間看其訊息是否是延遲收到,是的話則不處理,設為error返回。將接收到的訊息封裝為MessageExtBrokerInner。然後將其通過messageStore的putMessage方法將收到的訊息傳遞至儲存層處理,在這裡將儲存結果PutMessageResult等引數通過handlerPutMessageResult()處理。
這裡的messageStore採用的預設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;
}
這裡先檢測作業系統寫入是否忙,通過呼叫commitLog的putMessage()方法來儲存訊息,並記錄該方法的耗時eclipseTime設定到storeStatesServeice中,如果失敗,則storeStatesServeice的失敗次數加一。
我們來看下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;
}
從接收到的訊息中的sysFlag得到訊息的型別(事務、非事務、提交Commit型別),如果是非事務、提交型別則配置延遲交貨。
需要提一下,broker在儲存訊息的方式中採用MappedFileQueue方式,將不連續的物理檔案抽象成一串連續的邏輯檔案來處理。MapedFile管理具體的物理檔案的對映。所有訊息佇列的訊息的儲存均共用這裡的MappedFileQueue抽象的連續檔案進行訊息的儲存,用各自的各個訊息的偏移量offset在這裡取出具體的資料。
固定一個MappedFile的大小為MappedFileSize,那麼偏移量offset的訊息存於(offset-fileFromOffset)/MappedFileSize為下標的MappedFile中的低offset%fileFromOffset位元組開始。
那麼存資料,無非找到最後的MappedFile,再加鎖,並設定beginLockTimestamp時間戳,如果此時發現取得的最後一個MappedFile為null或者滿了,那麼重新建立一個。
然後呼叫mappedFile的anppendMessage並傳入要儲存的訊息跟appendMessageCallback,通過MappedFile物件寫入檔案,得到AppendMessageResult。
最後根據AppendMessageResult的結果來判斷訊息寫入檔案的情況,此時可能訊息過長MappedFile剩餘的部分不夠寫,重新申請一個mappedFile並呼叫其anppendMessage。
然後計算處理的總時間,解鎖。最後根據刷盤策略刷盤、主從同步。
appendMessage()方法直接呼叫了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);
}
我們可以看到這裡邏輯並不複雜,其呼叫了callBack的doAppend方法,其實現實在傳入的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;
}
先計算出已經寫了的偏移量wroteOffset
構造msgId,msgId的格式4byte的ip+4byte的port+8byte的wroteOffset
然後構造key,key的格式: topic-訊息佇列Id,然後根據key從topicQueueTable中查詢指定topic指定訊息佇列下的偏移量,如果找不到,那預設為0,並以鍵值對形式加入topicQueueTable中。
判斷訊息的型別,進行不同的處理。當然訊息的長度不能大於maxMessageSize。
按照一定的格式,將接收到的訊息寫到byteBuffer即(writenBuffer)中。
然後構造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;
}
追加訊息結果status、訊息的偏移量wroteOffset(相對於整個commitlog)、訊息待寫入位元組wroteBytes、訊息ID msgI、訊息寫入時間戳storeTimestamp、訊息佇列偏移量queueOffset、pagecacheRT。
返回到mappedFile的appendMessageInner方法中,當把訊息封裝到mappedFile的writeBuffer中後,更新writePosition跟storeTimestamp後返回。
返回到CommitLog的putMessage中,退出同步。進行訊息刷寫,我們來看下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();
}
}
}
分為同步跟非同步兩種方式,我們先來看下同步的方式。
同步方式下有兩種配置,一種是收到等待訊息儲存ok的訊息才返回,預設為true。進去條件分支後,我們看到其構造了GroupCommitRequest,並呼叫其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;
}
}
可以看到這個方法後,主執行緒停在了同步屏障上,等待其他執行緒cutDown。由於DefaultMessageStore的啟動,CommitLog的start方法即在其啟動的時候已經呼叫 public void start() {
this.flushCommitLogService.start();
if (defaultMessageStore.getMessageStoreConfig().isTransientStorePoolEnable()) {
this.commitLogService.start();
}
}
我們先來看下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,後臺有一個執行緒不停的執行doCommit方法,然後等待10毫秒,我們看下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);
}
}
}
我們可以看到呼叫mappedFileQueue.flush方法將資料進行向檔案中沖刷。對於每條訊息這兒起了兩次迴圈,可以理解到萬一有一條訊息一部分處於一個檔案尾,一部分處於另一個檔案頭,於是需要兩次沖刷,但一條訊息最多需要兩次,大部分都是一次。
沖刷完畢後,呼叫req.wakeupCustomer方法,讓在同步屏障等待的執行緒衝過同步屏障,因為此時訊息沖刷已經完成。
我們看下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;
}
通過每個訊息的offset得到具體的mappedFile,呼叫mappedFile的flush完成刷盤,剩下無非是offset的計算,跟時間戳。我們繼續跟下去。 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();
}
到這裡我們就可以看到通過呼叫fileChannel的force方法沖刷訊息。但此時又有疑問了,我們把訊息寫到了writeBuffer中,什麼時候writerBuffer中的訊息跑到了fileChannel中,僅通過fileChannel的force方法即可強制將其寫入檔案磁碟中?我們忽略了另一個serveice的run方法。
此時看到CommitLog的start方法,如果我們採用了TransientStorePool,即使用writeBuffer,那麼啟動commitLogService,我們看其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");
}
可以看到其也是呼叫mappedFileQueue的commit方法,然後呼叫waitForRunning等待配置的時長,再繼續迴圈。我們比較關心的是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;
}
計算偏移量得到mappedFile,再呼叫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();
}
看到這裡相比那個疑惑解決了,在後臺有個執行緒不斷的把writeBuffer寫到fileChannel中,然後刷盤只要把fileChannel中的資料寫入到磁碟中就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);
}
}
}
其實非同步的更簡單,直接喚醒commitLogService讓其將writeBuffer中的資料寫到fileChannel中,再讓fileChannel先空閒時候自己寫入磁碟,不強制寫入。可以思考下,為什麼要開啟writeBuffer?刷盤是無需同步的,但是把接收到的訊息存到本地記憶體中的時候是需要在同步塊中進行的,因此採用記憶體位元組緩衝區,可提高訊息插入的效能。再一步思考,同步刷盤效能應該是低於非同步,首先它配置了等結果的話他需要等待,更多的原因是呼叫fileChannel的force方法強制寫入效能會低於,filechannel在其空閒時寫入,增加程式整體效能。(由於本人接觸的水平有限,思考可能有錯,如果有問題望指出)
到這裡broker對接收到的訊息的儲存算是分析完了,接下來呼叫handleHA進行主從同步。