前面讲解到对于consumequeue的文件恢复和过期文件删除，和flush的过程这边就不再重点阐述，实际上consumequeue中的存储单元是一个20个字节的数据，前8个字节存储消息在commitlog上的物理点位，接着是4字节的消息size，最后是8字节的tag的hash值。可以看做消息在consumequeue上存储的是逻辑点位，作为commitlog中的索引。
存储结构
load过程
public boolean load() {
File dir = new File(this.storePath);
File[] files = dir.listFiles();
if (files != null) {
// ascending order
Arrays.sort(files);
for (File file : files) {
if (file.length() != this.mappedFileSize) {
log.warn(file + "\t" + file.length()
+ " length not matched message store config value, ignore it");
return true;
}
try {
// 每一个物理文件 建立mmap
MappedFile mappedFile = new MappedFile(file.getPath(), mappedFileSize);
// 初始化点位
mappedFile.setWrotePosition(this.mappedFileSize);
mappedFile.setFlushedPosition(this.mappedFileSize);
mappedFile.setCommittedPosition(this.mappedFileSize);
this.mappedFiles.add(mappedFile);
log.info("load " + file.getPath() + " OK");
} catch (IOException e) {
log.error("load file " + file + " error", e);
return false;
}
}
}
return true;
}
dispatch过程
dispatch过程发生在ReputMessageService中，用于构建consumequeue和index中的索引数据。对于consumequeue主要实现在CommitLogDispatcherBuildConsumeQueue中
class CommitLogDispatcherBuildConsumeQueue implements CommitLogDispatcher {
@Override
public void dispatch(DispatchRequest request) {
final int tranType = MessageSysFlag.getTransactionValue(request.getSysFlag());
switch (tranType) {
case MessageSysFlag.TRANSACTION_NOT_TYPE:
case MessageSysFlag.TRANSACTION_COMMIT_TYPE:
DefaultMessageStore.this.putMessagePositionInfo(request);
break;
case MessageSysFlag.TRANSACTION_PREPARED_TYPE:
case MessageSysFlag.TRANSACTION_ROLLBACK_TYPE:
break;
}
}
}
接下来put message 允许30次的失败重试，如果全部失败则会设置运行状态标志WRITE_LOGICS_QUEUE_ERROR_BIT，如果写成功 则更新checkpoint。再次详解putMessage的过程
private boolean putMessagePositionInfo(final long offset, final int size, final long tagsCode,
final long cqOffset) {
// 说明对该数据已经完成了dispatch
if (offset <= this.maxPhysicOffset) {
return true;
}
this.byteBufferIndex.flip();
this.byteBufferIndex.limit(CQ_STORE_UNIT_SIZE);
this.byteBufferIndex.putLong(offset);
this.byteBufferIndex.putInt(size);
this.byteBufferIndex.putLong(tagsCode);
final long expectLogicOffset = cqOffset * CQ_STORE_UNIT_SIZE;
// 此处可能会建立文件
MappedFile mappedFile = this.mappedFileQueue.getLastMappedFile(expectLogicOffset);
if (mappedFile != null) {
if (mappedFile.isFirstCreateInQueue() && cqOffset != 0 && mappedFile.getWrotePosition() == 0) {
this.minLogicOffset = expectLogicOffset;
// 设置flushedWhere 用于flush点位比较
this.mappedFileQueue.setFlushedWhere(expectLogicOffset);
this.mappedFileQueue.setCommittedWhere(expectLogicOffset);
this.fillPreBlank(mappedFile, expectLogicOffset);
log.info("fill pre blank space " + mappedFile.getFileName() + " " + expectLogicOffset + " "
+ mappedFile.getWrotePosition());
}
if (cqOffset != 0) {
long currentLogicOffset = mappedFile.getWrotePosition() + mappedFile.getFileFromOffset();
if (expectLogicOffset != currentLogicOffset) {
LOG_ERROR.warn(
"[BUG]logic queue order maybe wrong, expectLogicOffset: {} currentLogicOffset: {} Topic: {} QID: {} Diff: {}",
expectLogicOffset,
currentLogicOffset,
this.topic,
this.queueId,
expectLogicOffset - currentLogicOffset
);
}
}
this.maxPhysicOffset = offset;
// 写数据的具体逻辑
return mappedFile.appendMessage(this.byteBufferIndex.array());
}
return false;
}
最后面的写数据相对简单，判断写入后的数据是否小于文件大小，如果是则设置fileChannel的position，然后write，最后更新写位置。
public boolean appendMessage(final byte[] data) {
int currentPos = this.wrotePosition.get();
if ((currentPos + data.length) <= this.fileSize) {
try {
this.fileChannel.position(currentPos);
this.fileChannel.write(ByteBuffer.wrap(data));
} catch (Throwable e) {
log.error("Error occurred when append message to mappedFile.", e);
}
this.wrotePosition.addAndGet(data.length);
return true;
}
return false;
}
接下来讲解一下mappedFileQueue.getLastMappedFile，如何根据逻辑点位来获取到对于的MappedFile.
public MappedFile getLastMappedFile(final long startOffset, boolean needCreate) {
long createOffset = -1;
MappedFile mappedFileLast = getLastMappedFile();
if (mappedFileLast == null) {
// 文件头的offset
createOffset = startOffset - (startOffset % this.mappedFileSize);
}
// 对最后一个mappedFile进行判断，如果满了，则计算系哦啊一个文件的起始offset
if (mappedFileLast != null && mappedFileLast.isFull()) {
createOffset = mappedFileLast.getFileFromOffset() + this.mappedFileSize;
}
if (createOffset != -1 && needCreate) {
String nextFilePath = this.storePath + File.separator + UtilAll.offset2FileName(createOffset);
String nextNextFilePath = this.storePath + File.separator
+ UtilAll.offset2FileName(createOffset + this.mappedFileSize);
MappedFile mappedFile = null;
// 包含了预加载
if (this.allocateMappedFileService != null) {
mappedFile = this.allocateMappedFileService.putRequestAndReturnMappedFile(nextFilePath,
nextNextFilePath, this.mappedFileSize);
} else {
try {
// 创建mmap
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;
}
AllocateMappedFileService#putRequestAndReturnMappedFile会封装AllocateRequest并投递到requestQueue，然后由一个循环线程不断地读取队列获取request并创建mmap。
public MappedFile putRequestAndReturnMappedFile(String nextFilePath, String nextNextFilePath, int fileSize) {
int canSubmitRequests = 2;
if (this.messageStore.getMessageStoreConfig().isTransientStorePoolEnable()) {
if (this.messageStore.getMessageStoreConfig().isFastFailIfNoBufferInStorePool()
&& BrokerRole.SLAVE != this.messageStore.getMessageStoreConfig().getBrokerRole()) { //if broker is slave, don't fast fail even no buffer in pool
// 计算还能接收多少个AllocateRequest 内存池分配的数量 - 当前在排队中的请求
canSubmitRequests = this.messageStore.getTransientStorePool().remainBufferNumbs() - this.requestQueue.size();
}
}
AllocateRequest nextReq = new AllocateRequest(nextFilePath, fileSize);
boolean nextPutOK = this.requestTable.putIfAbsent(nextFilePath, nextReq) == null;
if (nextPutOK) {
if (canSubmitRequests <= 0) {
log.warn("[NOTIFYME]TransientStorePool is not enough, so create mapped file error, " +
"RequestQueueSize : {}, StorePoolSize: {}", this.requestQueue.size(), this.messageStore.getTransientStorePool().remainBufferNumbs());
this.requestTable.remove(nextFilePath);
return null;
}
boolean offerOK = this.requestQueue.offer(nextReq);
if (!offerOK) {
log.warn("never expected here, add a request to preallocate queue failed");
}
canSubmitRequests--;
}
// 下下个文件也创建请求
AllocateRequest nextNextReq = new AllocateRequest(nextNextFilePath, fileSize);
boolean nextNextPutOK = this.requestTable.putIfAbsent(nextNextFilePath, nextNextReq) == null;
if (nextNextPutOK) {
if (canSubmitRequests <= 0) {
log.warn("[NOTIFYME]TransientStorePool is not enough, so skip preallocate mapped file, " +
"RequestQueueSize : {}, StorePoolSize: {}", this.requestQueue.size(), this.messageStore.getTransientStorePool().remainBufferNumbs());
this.requestTable.remove(nextNextFilePath);
} else {
boolean offerOK = this.requestQueue.offer(nextNextReq);
if (!offerOK) {
log.warn("never expected here, add a request to preallocate queue failed");
}
}
}
if (hasException) {
log.warn(this.getServiceName() + " service has exception. so return null");
return null;
}
AllocateRequest result = this.requestTable.get(nextFilePath);
try {
if (result != null) {
// 同步等待文件创建结果
boolean waitOK = result.getCountDownLatch().await(waitTimeOut, TimeUnit.MILLISECONDS);
if (!waitOK) {
log.warn("create mmap timeout " + result.getFilePath() + " " + result.getFileSize());
return null;
} else {
this.requestTable.remove(nextFilePath);
return result.getMappedFile();
}
} else {
log.error("find preallocate mmap failed, this never happen");
}
} catch (InterruptedException e) {
log.warn(this.getServiceName() + " service has exception. ", e);
}
return null;
}
而在run方法内会不断地执行mmapOperation
private boolean mmapOperation() {
boolean isSuccess = false;
AllocateRequest req = null;
try {
// 从队列中拉取请求
req = this.requestQueue.take();
AllocateRequest expectedRequest = this.requestTable.get(req.getFilePath());
if (null == expectedRequest) {
log.warn("this mmap request expired, maybe cause timeout " + req.getFilePath() + " "
+ req.getFileSize());
return true;
}
if (expectedRequest != req) {
log.warn("never expected here, maybe cause timeout " + req.getFilePath() + " "
+ req.getFileSize() + ", req:" + req + ", expectedRequest:" + expectedRequest);
return true;
}
if (req.getMappedFile() == null) {
long beginTime = System.currentTimeMillis();
MappedFile mappedFile;
if (messageStore.getMessageStoreConfig().isTransientStorePoolEnable()) {
try {
mappedFile = ServiceLoader.load(MappedFile.class).iterator().next();
// 使用对外内存池来映射文件
mappedFile.init(req.getFilePath(), req.getFileSize(), messageStore.getTransientStorePool());
} catch (RuntimeException e) {
log.warn("Use default implementation.");
mappedFile = new MappedFile(req.getFilePath(), req.getFileSize(), messageStore.getTransientStorePool());
}
} else {
mappedFile = new MappedFile(req.getFilePath(), req.getFileSize());
}
long eclipseTime = UtilAll.computeEclipseTimeMilliseconds(beginTime);
if (eclipseTime > 10) {
int queueSize = this.requestQueue.size();
log.warn("create mappedFile spent time(ms) " + eclipseTime + " queue size " + queueSize
+ " " + req.getFilePath() + " " + req.getFileSize());
}
//预热 commitlog，每一个pagecache都会初始化一个数据
if (mappedFile.getFileSize() >= this.messageStore.getMessageStoreConfig()
.getMapedFileSizeCommitLog()
&&
this.messageStore.getMessageStoreConfig().isWarmMapedFileEnable()) {
mappedFile.warmMappedFile(this.messageStore.getMessageStoreConfig().getFlushDiskType(),
this.messageStore.getMessageStoreConfig().getFlushLeastPagesWhenWarmMapedFile());
}
req.setMappedFile(mappedFile);
this.hasException = false;
isSuccess = true;
}
} catch (InterruptedException e) {
log.warn(this.getServiceName() + " interrupted, possibly by shutdown.");
this.hasException = true;
return false;
} catch (IOException e) {
log.warn(this.getServiceName() + " service has exception. ", e);
this.hasException = true;
if (null != req) {
requestQueue.offer(req);
try {
Thread.sleep(1);
} catch (InterruptedException ignored) {
}
}
} finally {
if (req != null && isSuccess)
req.getCountDownLatch().countDown();
}
return true;
}
这里边重要的是确定了使用对外内存池还是堆内内存，还有对commitlog的预加载
**
* ！！预热 PUT数据的时候
* TODO 这里面会预先写数据
* @param type
* @param pages
*/
public void warmMappedFile(FlushDiskType type, int pages) {
long beginTime = System.currentTimeMillis();
ByteBuffer byteBuffer = this.mappedByteBuffer.slice();
int flush = 0;
long time = System.currentTimeMillis();
for (int i = 0, j = 0; i < this.fileSize; i += MappedFile.OS_PAGE_SIZE, j++) {
// 在一个4K的pagecache中，起始position写入一个字节
byteBuffer.put(i, (byte) 0);
// force flush when flush disk type is sync
//每写完一个pagecache 就flush
if (type == FlushDiskType.SYNC_FLUSH) {
if ((i / OS_PAGE_SIZE) - (flush / OS_PAGE_SIZE) >= pages) {
flush = i;
mappedByteBuffer.force();
}
}
// prevent gc
if (j % 1000 == 0) {
log.info("j={}, costTime={}", j, System.currentTimeMillis() - time);
time = System.currentTimeMillis();
try {
Thread.sleep(0);
} catch (InterruptedException e) {
log.error("Interrupted", e);
}
}
}
// force flush when prepare load finished
if (type == FlushDiskType.SYNC_FLUSH) {
log.info("mapped file warm-up done, force to disk, mappedFile={}, costTime={}",
this.getFileName(), System.currentTimeMillis() - beginTime);
mappedByteBuffer.force();
}
log.info("mapped file warm-up done. mappedFile={}, costTime={}", this.getFileName(),
System.currentTimeMillis() - beginTime);
// mlock目的就是把mappedByteBuffer内存在炒作系统层面给占用着，避免被重新分配 ，内部调用LibC.INSTANCE.mlock
this.mlock();
}