c# - 在 C# 中快速读取 100+ GB 文件中的行的最快方法

Question

正在处理一个将加载 100+ GB 文本文件的项目，其中一个过程是计算指定文件中的行数。我必须按照以下方式执行此操作，以免出现内存异常。有没有更快的方法或者最有效的方法来处理多任务。 (我知道你可以做一些事情，比如在 4 个线程上运行它，然后将组合输出除以 4。不知道最有效的方法)

uint loadCount2 = 0;
foreach (var line in File.ReadLines(currentPath))
{
    loadCount2++;
}

当我修复了程序的位置后，计划在具有 4 个双核 CPU 和 40 GB RAM 的服务器上运行该程序。目前，它运行在临时的小型 4 核 8GB RAM 服务器上。 (不知道线程在多个 CPU 上的表现如何。)

---

我测试了很多你的建议。

            Stopwatch sw2 = Stopwatch.StartNew();
            {
                using (FileStream fs = File.Open(json, FileMode.Open))
                    CountLinesMaybe(fs);
            }



            TimeSpan t = TimeSpan.FromMilliseconds(sw2.ElapsedMilliseconds);
            string answer = string.Format("{0:D2}h:{1:D2}m:{2:D2}s:{3:D3}ms", t.Hours, t.Minutes, t.Seconds, t.Milliseconds);
            Console.WriteLine(answer);
            sw2.Restart();
            loadCount2 = 0;


            Parallel.ForEach(File.ReadLines(json), (line) =>
            {
                loadCount2++;
            });


            t = TimeSpan.FromMilliseconds(sw2.ElapsedMilliseconds);
            answer = string.Format("{0:D2}h:{1:D2}m:{2:D2}s:{3:D3}ms", t.Hours, t.Minutes, t.Seconds, t.Milliseconds);
            Console.WriteLine(answer);
            sw2.Restart();
            loadCount2 = 0;

            foreach (var line in File.ReadLines(json))
            {
                loadCount2++;
            }

             t = TimeSpan.FromMilliseconds(sw2.ElapsedMilliseconds);
             answer = string.Format("{0:D2}h:{1:D2}m:{2:D2}s:{3:D3}ms", t.Hours, t.Minutes, t.Seconds, t.Milliseconds);
            Console.WriteLine(answer);
            sw2.Restart();
            loadCount2 = 0;

            int query = (int)Convert.ToByte('\n');
            using (var stream = File.OpenRead(json))
            {
                int current;
                do
                {
                    current = stream.ReadByte();
                    if (current == query)
                    {
                        loadCount2++;
                        continue;
                    }
                } while (current != -1);
            }

             t = TimeSpan.FromMilliseconds(sw2.ElapsedMilliseconds);
             answer = string.Format("{0:D2}h:{1:D2}m:{2:D2}s:{3:D3}ms", t.Hours, t.Minutes, t.Seconds, t.Milliseconds);
            Console.WriteLine(answer);
            Console.ReadKey();

---

    private const char CR = '\r';
    private const char LF = '\n';
    private const char NULL = (char)0;

    public static long CountLinesMaybe(Stream stream)
    {
        //Ensure.NotNull(stream, nameof(stream));

        var lineCount = 0L;

        var byteBuffer = new byte[1024 * 1024];
        const int BytesAtTheTime = 4;
        var detectedEOL = NULL;
        var currentChar = NULL;

        int bytesRead;
        while ((bytesRead = stream.Read(byteBuffer, 0, byteBuffer.Length)) > 0)
        {
            var i = 0;
            for (; i <= bytesRead - BytesAtTheTime; i += BytesAtTheTime)
            {
                currentChar = (char)byteBuffer[i];

                if (detectedEOL != NULL)
                {
                    if (currentChar == detectedEOL) { lineCount++; }

                    currentChar = (char)byteBuffer[i + 1];
                    if (currentChar == detectedEOL) { lineCount++; }

                    currentChar = (char)byteBuffer[i + 2];
                    if (currentChar == detectedEOL) { lineCount++; }

                    currentChar = (char)byteBuffer[i + 3];
                    if (currentChar == detectedEOL) { lineCount++; }
                }
                else
                {
                    if (currentChar == LF || currentChar == CR)
                    {
                        detectedEOL = currentChar;
                        lineCount++;
                    }
                    i -= BytesAtTheTime - 1;
                }
            }

            for (; i < bytesRead; i++)
            {
                currentChar = (char)byteBuffer[i];

                if (detectedEOL != NULL)
                {
                    if (currentChar == detectedEOL) { lineCount++; }
                }
                else
                {
                    if (currentChar == LF || currentChar == CR)
                    {
                        detectedEOL = currentChar;
                        lineCount++;
                    }
                }
            }
        }

        if (currentChar != LF && currentChar != CR && currentChar != NULL)
        {
            lineCount++;
        }
        return lineCount;
    }

结果显示出很大的进步，但我希望达到 20 分钟。 我希望他们在我更强大的服务器上这样做，看看拥有更多 CPU 的效果。

第二次运行返回: 23分钟， 25分钟， 22分钟， 29 分钟

这意味着这些方法实际上没有任何区别。 (无法截图，因为我取消了暂停，程序通过清屏继续)

Answer 1

基于 ReadByte(并与换行符比较)的方法可能比 ReadLine 更快。例如，对于更接近 GB 的文件

stopwatch = System.Diagnostics.Stopwatch.StartNew();
uint count = 0;
int query = (int)Convert.ToByte('\n');
using (var stream = File.OpenRead(filepath))
{
    int current;
    do
    {
        current = stream.ReadByte();
        if (current == query)
        {
            count++;
            continue;
        }
    } while (current!= -1);
}
Console.WriteLine($"Using ReadByte,Time : {stopwatch.Elapsed.TotalMilliseconds},Count: {r}");

使用ReadByte，时间:8174.5661，计数:7555107

stopwatch = System.Diagnostics.Stopwatch.StartNew();
uint loadCount2 = 0;
foreach (var line in File.ReadLines(filepath))
{
    loadCount2++;
}
Console.WriteLine($"Using ReadLines, Time : {stopwatch.Elapsed.TotalMilliseconds},Count: {r}");

使用 ReadLines，时间:27303.835，计数:7555107