19
我有一个结构，以3个整数存储3d坐标。在一个测试中，我将百万个随机点列表放在一起，然后将二进制序列化用于内存流。提高大型结构列表的二进制序列化性能
内存流是在1〜21 MB未来 - 这似乎1000000点非常低效的* 3个* COORDS 4个字节应该在11MB最低出来
它也正在〜3秒对我的试验台。
提高性能和/或大小的任何想法？
（我没有保持ISerialzable接口，如果有帮助，我可以直接写出到内存流）
编辑 - 从下面的答案我已经把一个序列化摊牌比较的BinaryFormatter ， '原始' 的BinaryWriter和的Protobuf
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，这只是看速度/大小，并没有考虑到其他任何东西。
@Ryan，[这个答案]（http://stackoverflow.com/questions/703073/what- （内置二进制格式化基础的网络序列化/ 703361＃703361）建议使用[protobuf-net]（http://code.google.com/p/protobuf-net）用于快速序列化。 – bzlm
@Ryan和protobuf-net“v2”支持结构。让我稍后再看看（目前不在PC上），但这是一个明确的选择。 –
二进制序列化使用反射。这很慢，但从来不是一个真正的问题，因为您将它用于I/O。为什么你序列化到内存是不可想象的。 –