"Chunked" MemoryStream

Question

I'm looking for the implementation of MemoryStream which does not allocate memory as one big block, but rather a collection of chunks. I want to store a few GB of data in memory (64 bit) and avoid limitation of memory fragmentation.

Answer 1

You need to first determine if virtual address fragmentation is the problem.

If you are on a 64 bit machine (which you seem to indicate you are) I seriously doubt it is. Each 64 bit process has almost the the entire 64 bit virtual memory space available and your only worry is virtual address space fragmentation not physical memory fragmentation (which is what the operating system must worry about). The OS memory manager already pages memory under the covers. For the forseeable future you will not run out of virtual address space before you run out of physical memory. This is unlikely change before we both retire.

If you are have a 32 bit address space, then allocating contiguous large blocks of memory in the GB ramge you will encounter a fragmentation problem quite quickly. There is no stock chunk allocating memory stream in the CLR. There is one in the under the covers in ASP.NET (for other reasons) but it is not accessable. If you must travel this path you are probably better off writing one youself anyway because the usage pattern of your application is unlikely to be similar to many others and trying to fit your data into a 32bit address space will likely be your perf bottleneck.

I highly recommend requiring a 64 bit process if you are manipulating GBs of data. It will do a much better job than hand-rolled solutions to 32 bit address space fragmentation regardless of how cleaver you are.

Answer 2

Something like this:

class ChunkedMemoryStream : Stream
{
    private readonly List<byte[]> _chunks = new List<byte[]>();
    private int _positionChunk;
    private int _positionOffset;
    private long _position;

    public override bool CanRead
    {
        get { return true; }
    }

    public override bool CanSeek
    {
        get { return true; }
    }

    public override bool CanWrite
    {
        get { return true; }
    }

    public override void Flush() { }

    public override long Length
    {
        get { return _chunks.Sum(c => c.Length); }
    }

    public override long Position
    {
        get
        {
            return _position;
        }
        set
        {
            _position = value;

            _positionChunk = 0;

            while (_positionOffset != 0)
            {
                if (_positionChunk >= _chunks.Count)
                    throw new OverflowException();

                if (_positionOffset < _chunks[_positionChunk].Length)
                    return;

                _positionOffset -= _chunks[_positionChunk].Length;
                _positionChunk++;
            }
        }
    }

    public override int Read(byte[] buffer, int offset, int count)
    {
        int result = 0;
        while ((count != 0) && (_positionChunk != _chunks.Count))
        {
            int fromChunk = Math.Min(count, _chunks[_positionChunk].Length - _positionOffset);
            if (fromChunk != 0)
            {
                Array.Copy(_chunks[_positionChunk], _positionOffset, buffer, offset, fromChunk);
                offset += fromChunk;
                count -= fromChunk;
                result += fromChunk;
                _position += fromChunk;
            }

            _positionOffset = 0;
            _positionChunk++;
        }
        return result;
    }

    public override long Seek(long offset, SeekOrigin origin)
    {
        long newPos = 0;

        switch (origin)
        {
            case SeekOrigin.Begin:
                newPos = offset;
                break;
            case SeekOrigin.Current:
                newPos = Position + offset;
                break;
            case SeekOrigin.End:
                newPos = Length - offset;
                break;
        }

        Position = Math.Max(0, Math.Min(newPos, Length));
        return newPos;
    }

    public override void SetLength(long value)
    {
        throw new NotImplementedException();
    }

    public override void Write(byte[] buffer, int offset, int count)
    {
        while ((count != 0) && (_positionChunk != _chunks.Count))
        {
            int toChunk = Math.Min(count, _chunks[_positionChunk].Length - _positionOffset);
            if (toChunk != 0)
            {
                Array.Copy(buffer, offset, _chunks[_positionChunk], _positionOffset, toChunk);
                offset += toChunk;
                count -= toChunk;
                _position += toChunk;
            }

            _positionOffset = 0;
            _positionChunk++;
        }

        if (count != 0)
        {
            byte[] chunk = new byte[count];
            Array.Copy(buffer, offset, chunk, 0, count);
            _chunks.Add(chunk);
            _positionChunk = _chunks.Count;
            _position += count;
        }
    }
}

class Program
{
    static void Main(string[] args)
    {
        ChunkedMemoryStream cms = new ChunkedMemoryStream();

        Debug.Assert(cms.Length == 0);
        Debug.Assert(cms.Position == 0);

        cms.Position = 0;

        byte[] helloworld = Encoding.UTF8.GetBytes("hello world");

        cms.Write(helloworld, 0, 3);
        cms.Write(helloworld, 3, 3);
        cms.Write(helloworld, 6, 5);

        Debug.Assert(cms.Length == 11);
        Debug.Assert(cms.Position == 11);

        cms.Position = 0;

        byte[] b = new byte[20];
        cms.Read(b, 3, (int)cms.Length);
        Debug.Assert(b.Skip(3).Take(11).SequenceEqual(helloworld));

        cms.Position = 0;
        cms.Write(Encoding.UTF8.GetBytes("seeya"), 0, 5);

        Debug.Assert(cms.Length == 11);
        Debug.Assert(cms.Position == 5);

        cms.Position = 0;
        cms.Read(b, 0, (byte) cms.Length);
        Debug.Assert(b.Take(11).SequenceEqual(Encoding.UTF8.GetBytes("seeya world")));

        Debug.Assert(cms.Length == 11);
        Debug.Assert(cms.Position == 11);

        cms.Write(Encoding.UTF8.GetBytes(" again"), 0, 6);

        Debug.Assert(cms.Length == 17);
        Debug.Assert(cms.Position == 17);

        cms.Position = 0;
        cms.Read(b, 0, (byte)cms.Length);
        Debug.Assert(b.Take(17).SequenceEqual(Encoding.UTF8.GetBytes("seeya world again")));

    }
}

Answer 3

you can use this

http://www.123aspx.com/Rotor/src/chunkedmemorystream.cs.txt