Libgit2sharp推动性能下降与许多提交

Question

我正在研究的项目以奇怪的方式使用GIT。基本上它一次写入并推送一个提交。该项目可能导致一个分支拥有数十万次提交。在测试时，我们发现只有大约500次提交后，GIT推送的性能开始下降。在使用过程监视器进行进一步调查后，我们认为降级是由于整个树的行走导致分支被推动。既然我们只是在任何给定时间推送一个新的提交，有没有办法优化它？

或者有没有办法将提交历史限制为50次提交以减少这种开销？

我正在使用LibGit2Sharp版本0.20.1.0

更新1

为了测试，我编写了以下代码：

void Main()
{
    string remotePath = @"E:\GIT Test\Remote";
    string localPath = @"E:\GIT Test\Local";
    string localFilePath = Path.Combine(localPath, "TestFile.txt");

    Repository.Init(remotePath, true);
    Repository.Clone(remotePath, localPath);

    Repository repo = new Repository(localPath);

    for(int i = 0; i < 2000; i++)
    {
        File.WriteAllText(localFilePath, RandomString((i % 2 + 1) * 10));
        repo.Stage(localFilePath);

        Commit commit = repo.Commit(
            string.Format("Commit number: {0}", i), 
            new Signature("TestAuthor", "TestEmail@Test.com", System.DateTimeOffset.Now),
            new Signature("TestAuthor", "TestEmail@Test.com", System.DateTimeOffset.Now));      

        Stopwatch pushWatch = Stopwatch.StartNew();
        Remote defaultRemote = repo.Network.Remotes["origin"];
        repo.Network.Push(defaultRemote, "refs/heads/master:refs/heads/master");
        pushWatch.Stop();
        Trace.WriteLine(string.Format("Push {0} took {1}ms", i, pushWatch.ElapsedMilliseconds));
    }
}

private const string Characters = "ABCDEFGHIJKLMNOPQRSTUVWXYZ";
private static readonly Random Random = new Random();

/// <summary>
/// Get a Random string of the specified length
/// </summary>
public static string RandomString(int size)
{
    char[] buffer = new char[size];

    for (int i = 0; i < size; i++)
    {
        buffer[i] = Characters[Random.Next(Characters.Length)];
    }

    return new string(buffer);
}

然后运行此处找到的进程监视器： http://technet.microsoft.com/en-us/sysinternals/bb896645.aspx

每次推送的时间一般都很低，随着时间的推移，频率和延迟都会增加。在查看进程监视器的输出时，我相信这些尖峰排列在一个很长的伸展位置，正在访问.git \ objects文件夹中的对象。由于某种原因偶尔会出现拉动，因此对象的大量读取在看得更近时似乎是在提交和对象中漫步。

以上流程是我们在项目中实际执行的实际流程的精简版本。在我们的实际流程中，我们首先从“Master”创建一个新的分支“Temp”，提交“Temp”，推送“Temp”，将“Temp”与“Master”合并然后推送“Master”。当我们对该流程的每个部分进行计时时，我们发现推送是迄今为止运行时间最长的操作，随着提交工作堆积在“Master”上，它的使用时间也在增加。

更新2 我最近更新使用libgit2sharp版本0.20.1.0，这个问题仍然存在。有谁知道为什么会这样？

更新3 我们更改了一些代码，以便在“Master”分支上创建第一次提交的临时分支，以减少提交树遍历开销，但发现它仍然存在。下面是一个应该易于编译和运行的示例。它显示了无论提交位置如何，在创建新分支时都会发生树遍历。为了查看树遍历，我使用了上面的进程监视工具和命令行GIT Bash来检查它打开的每个对象是什么。有谁知道为什么会这样？这是预期的行为还是我做错了什么？这似乎是导致问题的推动力。

void Main()
{
    string remotePath = @"E:\GIT Test\Remote";
    string localPath = @"E:\GIT Test\Local";
    string localFilePath = Path.Combine(localPath, "TestFile.txt");

    Repository.Init(remotePath, true);
    Repository.Clone(remotePath, localPath);

    // Setup Initial Commit
    string newBranch;
    using (Repository repo = new Repository(localPath))
    {
        CommitRandomFile(repo, 0, localFilePath, "master");
        newBranch = CreateNewBranch(repo, "master");
        repo.Checkout(newBranch);
    }

    // Commit 1000 times to the new branch
    for(int i = 1; i < 1001; i++)
    {
        using(Repository repo = new Repository(localPath))
        {
            CommitRandomFile(repo, i, localFilePath, newBranch);
        }
    }

    // Create a single new branch from the first commit ever
    // For some reason seems to walk the entire commit tree
    using(Repository repo = new Repository(localPath))
    {               
        CreateNewBranch(repo, "master");
    }
}

private const string Characters = "ABCDEFGHIJKLMNOPQRSTUVWXYZ";
private static readonly Random Random = new Random();

/// <summary>
/// Generate and commit a random file to the specified branch
/// </summary>
public static void CommitRandomFile(Repository repo, int seed, string rootPath, string branch)
{
    File.WriteAllText(rootPath, RandomString((seed % 2 + 1) * 10));
    repo.Stage(rootPath);

    Commit commit = repo.Commit(
        string.Format("Commit: {0}", seed), 
        new Signature("TestAuthor", "TestEmail@Test.com", System.DateTimeOffset.Now),
        new Signature("TestAuthor", "TestEmail@Test.com", System.DateTimeOffset.Now));      

    Stopwatch pushWatch = Stopwatch.StartNew();
    repo.Network.Push(repo.Network.Remotes["origin"], "refs/heads/" + branch + ":refs/heads/" + branch);
    pushWatch.Stop();

    Trace.WriteLine(string.Format("Push {0} took {1}ms", seed, pushWatch.ElapsedMilliseconds));
}

/// <summary>
/// Create a new branch from the specified source
/// </summary>
public static string CreateNewBranch(Repository repo, string sourceBranch)
{
    Branch source = repo.Branches[sourceBranch];
    string newBranch = Guid.NewGuid().ToString();
    repo.Branches.Add(newBranch, source.Tip);

    Stopwatch pushNewBranchWatch = Stopwatch.StartNew();
    repo.Network.Push(repo.Network.Remotes["origin"], "refs/heads/" + newBranch + ":refs/heads/" + newBranch);
    pushNewBranchWatch.Stop();

    Trace.WriteLine(string.Format("Push of new branch {0} took {1}ms", newBranch, pushNewBranchWatch.ElapsedMilliseconds));
    return newBranch;
}

/// <summary>
/// Get a Random string of the specified length
/// </summary>
public static string RandomString(int size)
{
    char[] buffer = new char[size];

    for (int i = 0; i < size; i++)
    {
        buffer[i] = Characters[Random.Next(Characters.Length)];
    }

    return new string(buffer);
}