c# - 提高大型结构列表的二进制序列化性能

Question

我有一个在 3 个整数中保存 3d 坐标的结构。在测试中，我将 100 万个随机点的列表<>放在一起，然后对内存流使用二进制序列化。

内存流的大小约为 21 MB - 这似乎非常低效，因为 1000000 点 * 3 坐标 * 4 字节应该至少为 11MB

它在我的测试装置上也需要大约 3 秒。

有什么改进性能和/或大小的想法吗？

(如果有帮助，我不必保留 ISerialzable 接口(interface)，我可以直接写入内存流)

编辑 - 根据下面的答案，我整理了一个比较 BinaryFormatter、'Raw' BinaryWriter 和 Protobuf 的序列化摊牌

using System;
using System.Text;
using System.Collections.Generic;
using System.Linq;
using Microsoft.VisualStudio.TestTools.UnitTesting;
using System.Runtime.Serialization;
using System.Runtime.Serialization.Formatters.Binary;
using System.IO;
using ProtoBuf;

namespace asp_heatmap.test
{
    [Serializable()] // For .NET BinaryFormatter
    [ProtoContract] // For Protobuf
    public class Coordinates : ISerializable
    {
        [Serializable()]
        [ProtoContract]
        public struct CoOrd
        {
            public CoOrd(int x, int y, int z)
            {
                this.x = x;
                this.y = y;
                this.z = z;
            }
            [ProtoMember(1)]            
            public int x;
            [ProtoMember(2)]
            public int y;
            [ProtoMember(3)]
            public int z;
        }

        internal Coordinates()
        {
        }

        [ProtoMember(1)]
        public List<CoOrd> Coords = new List<CoOrd>();

        public void SetupTestArray()
        {
            Random r = new Random();
            List<CoOrd> coordinates = new List<CoOrd>();
            for (int i = 0; i < 1000000; i++)
            {
                Coords.Add(new CoOrd(r.Next(), r.Next(), r.Next()));
            }
        }

        #region Using Framework Binary Formatter Serialization

        void ISerializable.GetObjectData(SerializationInfo info, StreamingContext context)
        {
            info.AddValue("Coords", this.Coords);
        }

        internal Coordinates(SerializationInfo info, StreamingContext context)
        {
            this.Coords = (List<CoOrd>)info.GetValue("Coords", typeof(List<CoOrd>));
        }

        #endregion

        # region 'Raw' Binary Writer serialization

        public MemoryStream RawSerializeToStream()
        {
            MemoryStream stream = new MemoryStream(Coords.Count * 3 * 4 + 4);
            BinaryWriter writer = new BinaryWriter(stream);
            writer.Write(Coords.Count);
            foreach (CoOrd point in Coords)
            {
                writer.Write(point.x);
                writer.Write(point.y);
                writer.Write(point.z);
            }
            return stream;
        }

        public Coordinates(MemoryStream stream)
        {
            using (BinaryReader reader = new BinaryReader(stream))
            {
                int count = reader.ReadInt32();
                Coords = new List<CoOrd>(count);
                for (int i = 0; i < count; i++)                
                {
                    Coords.Add(new CoOrd(reader.ReadInt32(),reader.ReadInt32(),reader.ReadInt32()));
                }
            }        
        }
        #endregion
    }

    [TestClass]
    public class SerializationTest
    {
        [TestMethod]
        public void TestBinaryFormatter()
        {
            Coordinates c = new Coordinates();
            c.SetupTestArray();

            // Serialize to memory stream
            MemoryStream mStream = new MemoryStream();
            BinaryFormatter bformatter = new BinaryFormatter();
            bformatter.Serialize(mStream, c);
            Console.WriteLine("Length : {0}", mStream.Length);

            // Now Deserialize
            mStream.Position = 0;
            Coordinates c2 = (Coordinates)bformatter.Deserialize(mStream);
            Console.Write(c2.Coords.Count);

            mStream.Close();
        }

        [TestMethod]
        public void TestBinaryWriter()
        {
            Coordinates c = new Coordinates();
            c.SetupTestArray();

            MemoryStream mStream = c.RawSerializeToStream();
            Console.WriteLine("Length : {0}", mStream.Length);

            // Now Deserialize
            mStream.Position = 0;
            Coordinates c2 = new Coordinates(mStream);
            Console.Write(c2.Coords.Count);
        }

        [TestMethod]
        public void TestProtoBufV2()
        {
            Coordinates c = new Coordinates();
            c.SetupTestArray();

            MemoryStream mStream = new MemoryStream();
            ProtoBuf.Serializer.Serialize(mStream,c);
            Console.WriteLine("Length : {0}", mStream.Length);

            mStream.Position = 0;
            Coordinates c2 = ProtoBuf.Serializer.Deserialize<Coordinates>(mStream);
            Console.Write(c2.Coords.Count);
        }
    }
}

结果 (注意 PB v2.0.0.423 测试版)

                Serialize | Ser + Deserialize    | Size
-----------------------------------------------------------          
BinaryFormatter    2.89s  |      26.00s !!!      | 21.0 MB
ProtoBuf v2        0.52s  |       0.83s          | 18.7 MB
Raw BinaryWriter   0.27s  |       0.36s          | 11.4 MB

显然这只是考虑速度/大小，并没有考虑任何其他因素。

Answer 1

使用 BinaryFormatter 的二进制序列化在其生成的字节中包含类型信息。这会占用额外的空间。例如，当您不知道另一端的数据结构时，它会很有用。

在您的情况下，您知道数据在两端的格式是什么，这听起来不会改变。所以你可以写一个简单的编码和解码方法。您的 CoOrd 类也不再需要可序列化。

我会使用 System.IO.BinaryReader 和 System.IO.BinaryWriter ，然后遍历每个 CoOrd 实例并将 X、Y、Z 属性值读/写到流中。假设您的许多数字小于 0x7F 和 0x7FFF，这些类甚至会将您的整数压缩到小于 11MB。

像这样:

using (var writer = new BinaryWriter(stream)) {
    // write the number of items so we know how many to read out
    writer.Write(points.Count);
    // write three ints per point
    foreach (var point in points) {
        writer.Write(point.X);
        writer.Write(point.Y);
        writer.Write(point.Z);
    }
}

从流中读取:

List<CoOrd> points;
using (var reader = new BinaryReader(stream)) {
    var count = reader.ReadInt32();
    points = new List<CoOrd>(count);
    for (int i = 0; i < count; i++) {
        var x = reader.ReadInt32();
        var y = reader.ReadInt32();
        var z = reader.ReadInt32();
        points.Add(new CoOrd(x, y, z));
    }
}