MappedFile 的创建和预热

// org.apache.rocketmq.store.AllocateMappedFileService
// 创建 MappedFile 的请求
static class AllocateRequest implements Comparable {
    // Full file path
    private String filePath;
    private int fileSize;
    private CountDownLatch countDownLatch = new CountDownLatch(1);
    private volatile MappedFile mappedFile = null;
}

创建 MappedFile 是一个异步的过程

// AllocateRequest 放在队列中
private PriorityBlockingQueue requestQueue = new PriorityBlockingQueue();

往队列中放入 AllocateRequest

public MappedFile putRequestAndReturnMappedFile(String nextFilePath, String nextNextFilePath, int fileSize) {
    int canSubmitRequests = 2;
    // 这个开关默认没有开启
    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
            canSubmitRequests = this.messageStore.getTransientStorePool().availableBufferNums() - this.requestQueue.size();
        }
    }

    AllocateRequest nextReq = new AllocateRequest(nextFilePath, fileSize);
    // 查询 requestTable 中是否有请求
    // requestTable 中不含请求，则 nextPutOK 为 true
    boolean nextPutOK = this.requestTable.putIfAbsent(nextFilePath, nextReq) == null;

    // 如果原来 requestTable 没有请求，则放入 requestQueue 中
    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().availableBufferNums());
            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--;
    }

    // 一次处理两个请求，处理方式同上面
    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().availableBufferNums());
            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) {
            boolean waitOK = result.getCountDownLatch().await(waitTimeOut, TimeUnit.MILLISECONDS);
            if (!waitOK) {
                log.warn("create mmap timeout " + result.getFilePath() + " " + result.getFileSize());
                return null;
            } else {
                // waitOK 为 true，表明 mappedFile 已创建好
                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;
}

从队列中取出 AllocateRequest，创建 MappedFile

// org.apache.rocketmq.store.AllocateMappedFileService#mmapOperation
private boolean mmapOperation() {
    boolean isSuccess = false;
    AllocateRequest req = null;
    try {
        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();
                    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 {
                // 创建 mappedFile
                mappedFile = new MappedFile(req.getFilePath(), req.getFileSize());
            }

            long elapsedTime = UtilAll.computeElapsedTimeMilliseconds(beginTime);
            if (elapsedTime > 10) {
                int queueSize = this.requestQueue.size();
                log.warn("create mappedFile spent time(ms) " + elapsedTime + " queue size " + queueSize
                    + " " + req.getFilePath() + " " + req.getFileSize());
            }

            // pre write mappedFile
            // 文件大小大于 1G，并且开启 warmMapedFileEnable
            if (mappedFile.getFileSize() >= this.messageStore.getMessageStoreConfig()
                .getMappedFileSizeCommitLog()
                &&
                this.messageStore.getMessageStoreConfig().isWarmMapedFileEnable()) {
                mappedFile.warmMappedFile(this.messageStore.getMessageStoreConfig().getFlushDiskType(),
                    this.messageStore.getMessageStoreConfig().getFlushLeastPagesWhenWarmMapedFile());
            }

            // 设置 mappedFile
            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 {
        // countDownLatch 减一
        if (req != null && isSuccess)
            req.getCountDownLatch().countDown();
    }
    return true;
}

文件预热开关，默认 false，如果设置为 true，则会对文件进行预热

org.apache.rocketmq.store.config.MessageStoreConfig#warmMapedFileEnable

// org.apache.rocketmq.store.MappedFile#warmMappedFile
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++) {
        // 每一个 4k 页，写入一个字节 0
        byteBuffer.put(i, (byte) 0);
        // force flush when flush disk type is sync
        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);
    
    this.mlock();
}

猜想：
通过 mmap 映射，操作系统只是建立了映射关系，并没有分配内存，通过在每一页中写入数据，才真正分配内存

通过 jna 锁住内存，防止操作系统把指定的内存区域交换到 swap 空间

public void mlock() {
    final long beginTime = System.currentTimeMillis();
    final long address = ((DirectBuffer) (this.mappedByteBuffer)).address();
    Pointer pointer = new Pointer(address);
    {
        int ret = LibC.INSTANCE.mlock(pointer, new NativeLong(this.fileSize));
        log.info("mlock {} {} {} ret = {} time consuming = {}", address, this.fileName, this.fileSize, ret, System.currentTimeMillis() - beginTime);
    }

    {
        int ret = LibC.INSTANCE.madvise(pointer, new NativeLong(this.fileSize), LibC.MADV_WILLNEED);
        log.info("madvise {} {} {} ret = {} time consuming = {}", address, this.fileName, this.fileSize, ret, System.currentTimeMillis() - beginTime);
    }
}

如果开启了预热，在创建新的文件时，老的文件会释放

public void munlock() {
    final long beginTime = System.currentTimeMillis();
    final long address = ((DirectBuffer) (this.mappedByteBuffer)).address();
    Pointer pointer = new Pointer(address);
    int ret = LibC.INSTANCE.munlock(pointer, new NativeLong(this.fileSize));
    log.info("munlock {} {} {} ret = {} time consuming = {}", address, this.fileName, this.fileSize, ret, System.currentTimeMillis() - beginTime);
}