String.Join vs. StringBuilder:哪个更快？

这是我的试验台,int[][]用于简单; 结果第一:

Join: 9420ms (chk: 210710000
OneBuilder: 9021ms (chk: 210710000

(更新double结果:)

Join: 11635ms (chk: 210710000
OneBuilder: 11385ms (chk: 210710000

(更新re 2048*64*150)

Join: 11620ms (chk: 206409600
OneBuilder: 11132ms (chk: 206409600

并启用OptimizeForTesting:

Join: 11180ms (chk: 206409600
OneBuilder: 10784ms (chk: 206409600

如此之快,但不是那么大; rig(在控制台上运行,在发布模式下运行等):

using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Text;

namespace ConsoleApplication2
{
    class Program
    {
        static void Collect()
        {
            GC.Collect(GC.MaxGeneration, GCCollectionMode.Forced);
            GC.WaitForPendingFinalizers();
            GC.Collect(GC.MaxGeneration, GCCollectionMode.Forced);
            GC.WaitForPendingFinalizers();
        }
        static void Main(string[] args)
        {
            const int ROWS = 500, COLS = 20, LOOPS = 2000;
            int[][] data = new int[ROWS][];
            Random rand = new Random(123456);
            for (int row = 0; row < ROWS; row++)
            {
                int[] cells = new int[COLS];
                for (int col = 0; col < COLS; col++)
                {
                    cells[col] = rand.Next();
                }
                data[row] = cells;
            }
            Collect();
            int chksum = 0;
            Stopwatch watch = Stopwatch.StartNew();
            for (int i = 0; i < LOOPS; i++)
            {
                chksum += Join(data).Length;
            }
            watch.Stop();
            Console.WriteLine("Join: {0}ms (chk: {1}", watch.ElapsedMilliseconds, chksum);

            Collect();
            chksum = 0;
            watch = Stopwatch.StartNew();
            for (int i = 0; i < LOOPS; i++)
            {
                chksum += OneBuilder(data).Length;
            }
            watch.Stop();
            Console.WriteLine("OneBuilder: {0}ms (chk: {1}", watch.ElapsedMilliseconds, chksum);

            Console.WriteLine("done");
            Console.ReadLine();
        }
        public static string Join(int[][] array)
        {
            return String.Join(Environment.NewLine,
                    Array.ConvertAll(array,
                      row => String.Join(",",
                        Array.ConvertAll(row, x => x.ToString()))));
        }
        public static string OneBuilder(IEnumerable source)
        {
            StringBuilder sb = new StringBuilder();
            bool firstRow = true;
            foreach (var row in source)
            {
                if (firstRow)
                {
                    firstRow = false;
                }
                else
                {
                    sb.AppendLine();
                }
                if (row.Length > 0)
                {
                    sb.Append(row[0]);
                    for (int i = 1; i < row.Length; i++)
                    {
                        sb.Append(',').Append(row[i]);
                    }
                }
            }
            return sb.ToString();
        }
    }
}

我不这么认为.透过Reflector看,执行效果String.Join非常优化.它还具有预先知道要创建的字符串总大小的额外好处,因此不需要任何重新分配.

我创建了两种测试方法来比较它们:

public static string TestStringJoin(double[][] array)
{
    return String.Join(Environment.NewLine,
        Array.ConvertAll(array,
            row => String.Join(",",
                       Array.ConvertAll(row, x => x.ToString()))));
}

public static string TestStringBuilder(double[][] source)
{
    // based on Marc Gravell's code

    StringBuilder sb = new StringBuilder();
    foreach (var row in source)
    {
        if (row.Length > 0)
        {
            sb.Append(row[0]);
            for (int i = 1; i < row.Length; i++)
            {
                sb.Append(',').Append(row[i]);
            }
        }
    }
    return sb.ToString();
}

我运行了每个方法50次,传入一个大小的数组[2048][64].我为两个阵列做了这个; 一个填充零,另一个填充随机值.我在我的机器上得到了以下结果(P4 3.0 GHz,单核,无HT,从CMD运行释放模式):

// with zeros:
TestStringJoin    took 00:00:02.2755280
TestStringBuilder took 00:00:02.3536041

// with random values:
TestStringJoin    took 00:00:05.6412147
TestStringBuilder took 00:00:05.8394650

增加数组的大小[2048][512],同时将迭代次数减少到10得到以下结果:

// with zeros:
TestStringJoin    took 00:00:03.7146628
TestStringBuilder took 00:00:03.8886978

// with random values:
TestStringJoin    took 00:00:09.4991765
TestStringBuilder took 00:00:09.3033365

结果是可重复的(几乎;由不同的随机值引起的小波动).显然String.Join大部分时间都要快一点(虽然幅度非常小).

这是我用于测试的代码:

const int Iterations = 50;
const int Rows = 2048;
const int Cols = 64; // 512

static void Main()
{
    OptimizeForTesting(); // set process priority to RealTime

    // test 1: zeros
    double[][] array = new double[Rows][];
    for (int i = 0; i < array.Length; ++i)
        array[i] = new double[Cols];

    CompareMethods(array);

    // test 2: random values
    Random random = new Random();
    double[] template = new double[Cols];
    for (int i = 0; i < template.Length; ++i)
        template[i] = random.NextDouble();

    for (int i = 0; i < array.Length; ++i)
        array[i] = template;

    CompareMethods(array);
}

static void CompareMethods(double[][] array)
{
    Stopwatch stopwatch = Stopwatch.StartNew();
    for (int i = 0; i < Iterations; ++i)
        TestStringJoin(array);
    stopwatch.Stop();
    Console.WriteLine("TestStringJoin    took " + stopwatch.Elapsed);

    stopwatch.Reset(); stopwatch.Start();
    for (int i = 0; i < Iterations; ++i)
        TestStringBuilder(array);
    stopwatch.Stop();
    Console.WriteLine("TestStringBuilder took " + stopwatch.Elapsed);

}

static void OptimizeForTesting()
{
    Thread.CurrentThread.Priority = ThreadPriority.Highest;
    Process currentProcess = Process.GetCurrentProcess();
    currentProcess.PriorityClass = ProcessPriorityClass.RealTime;
    if (Environment.ProcessorCount > 1) {
        // use last core only
        currentProcess.ProcessorAffinity
            = new IntPtr(1 << (Environment.ProcessorCount - 1));
    }
}

除非1%的差异在整个程序运行的时间内变成重要的东西,否则这看起来像微优化.我会编写最易读/可理解的代码,而不用担心1%的性能差异.