我有一个网络服务器,它将读取大二进制文件(几兆字节)到字节数组。服务器可能同时读取多个文件(不同的页面请求),因此我正在寻找一种最优化的方式来执行此操作,而不会对CPU造成太多负担。下面的代码足够好吗?

public byte[] FileToByteArray(string fileName)
{
    byte[] buff = null;
    FileStream fs = new FileStream(fileName, 
                                   FileMode.Open, 
                                   FileAccess.Read);
    BinaryReader br = new BinaryReader(fs);
    long numBytes = new FileInfo(fileName).Length;
    buff = br.ReadBytes((int) numBytes);
    return buff;
}

当前回答

In case with 'a large file' is meant beyond the 4GB limit, then my following written code logic is appropriate. The key issue to notice is the LONG data type used with the SEEK method. As a LONG is able to point beyond 2^32 data boundaries. In this example, the code is processing first processing the large file in chunks of 1GB, after the large whole 1GB chunks are processed, the left over (<1GB) bytes are processed. I use this code with calculating the CRC of files beyond the 4GB size. (using https://crc32c.machinezoo.com/ for the crc32c calculation in this example)

private uint Crc32CAlgorithmBigCrc(string fileName)
{
    uint hash = 0;
    byte[] buffer = null;
    FileInfo fileInfo = new FileInfo(fileName);
    long fileLength = fileInfo.Length;
    int blockSize = 1024000000;
    decimal div = fileLength / blockSize;
    int blocks = (int)Math.Floor(div);
    int restBytes = (int)(fileLength - (blocks * blockSize));
    long offsetFile = 0;
    uint interHash = 0;
    Crc32CAlgorithm Crc32CAlgorithm = new Crc32CAlgorithm();
    bool firstBlock = true;
    using (FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read))
    {
        buffer = new byte[blockSize];
        using (BinaryReader br = new BinaryReader(fs))
        {
            while (blocks > 0)
            {
                blocks -= 1;
                fs.Seek(offsetFile, SeekOrigin.Begin);
                buffer = br.ReadBytes(blockSize);
                if (firstBlock)
                {
                    firstBlock = false;
                    interHash = Crc32CAlgorithm.Compute(buffer);
                    hash = interHash;
                }
                else
                {
                    hash = Crc32CAlgorithm.Append(interHash, buffer);
                }
                offsetFile += blockSize;
            }
            if (restBytes > 0)
            {
                Array.Resize(ref buffer, restBytes);
                fs.Seek(offsetFile, SeekOrigin.Begin);
                buffer = br.ReadBytes(restBytes);
                hash = Crc32CAlgorithm.Append(interHash, buffer);
            }
            buffer = null;
        }
    }
    //MessageBox.Show(hash.ToString());
    //MessageBox.Show(hash.ToString("X"));
    return hash;
}

其他回答

用这个:

 bytesRead = responseStream.ReadAsync(buffer, 0, Length).Result;

简单地将整个内容替换为:

return File.ReadAllBytes(fileName);

但是,如果您关心内存消耗,就不应该将整个文件一次全部读入内存。你应该分块做。

我会这样想:

byte[] file = System.IO.File.ReadAllBytes(fileName);

如果您正在处理大于2 GB的文件,您会发现上述方法失败。

直接将流交给MD5并允许它为你分块文件要容易得多:

private byte[] computeFileHash(string filename)
{
    MD5 md5 = MD5.Create();
    using (FileStream fs = new FileStream(filename, FileMode.Open))
    {
        byte[] hash = md5.ComputeHash(fs);
        return hash;
    }
}

In case with 'a large file' is meant beyond the 4GB limit, then my following written code logic is appropriate. The key issue to notice is the LONG data type used with the SEEK method. As a LONG is able to point beyond 2^32 data boundaries. In this example, the code is processing first processing the large file in chunks of 1GB, after the large whole 1GB chunks are processed, the left over (<1GB) bytes are processed. I use this code with calculating the CRC of files beyond the 4GB size. (using https://crc32c.machinezoo.com/ for the crc32c calculation in this example)

private uint Crc32CAlgorithmBigCrc(string fileName)
{
    uint hash = 0;
    byte[] buffer = null;
    FileInfo fileInfo = new FileInfo(fileName);
    long fileLength = fileInfo.Length;
    int blockSize = 1024000000;
    decimal div = fileLength / blockSize;
    int blocks = (int)Math.Floor(div);
    int restBytes = (int)(fileLength - (blocks * blockSize));
    long offsetFile = 0;
    uint interHash = 0;
    Crc32CAlgorithm Crc32CAlgorithm = new Crc32CAlgorithm();
    bool firstBlock = true;
    using (FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read))
    {
        buffer = new byte[blockSize];
        using (BinaryReader br = new BinaryReader(fs))
        {
            while (blocks > 0)
            {
                blocks -= 1;
                fs.Seek(offsetFile, SeekOrigin.Begin);
                buffer = br.ReadBytes(blockSize);
                if (firstBlock)
                {
                    firstBlock = false;
                    interHash = Crc32CAlgorithm.Compute(buffer);
                    hash = interHash;
                }
                else
                {
                    hash = Crc32CAlgorithm.Append(interHash, buffer);
                }
                offsetFile += blockSize;
            }
            if (restBytes > 0)
            {
                Array.Resize(ref buffer, restBytes);
                fs.Seek(offsetFile, SeekOrigin.Begin);
                buffer = br.ReadBytes(restBytes);
                hash = Crc32CAlgorithm.Append(interHash, buffer);
            }
            buffer = null;
        }
    }
    //MessageBox.Show(hash.ToString());
    //MessageBox.Show(hash.ToString("X"));
    return hash;
}