Warum ist C <stdio.h> FILE* fread() schneller als Win32 ReadFile()?

Vergleich Lesen von Dateien mithilfe der folgenden drei Methoden:

1. C <stdio.h> FILE*
2. Win32 CreateFile()/ReadFile()
3. Win32 memory mapping

Bemerkte ich, dass #1 ist schneller als die #2, und #3 ist die Schnellste.

z.B. in der Reihenfolge der schnellsten zum langsamsten, für die Bearbeitung einer 900MB Datei test, ich bekam diese Ergebnisse:

Win32-Speicher-mapping: 821.308 ms

C-Datei (FILE*): 1779.83 ms

Win32-Datei (CreateFile): 3649.67 ms

Warum ist die C <stdio.h> Technik schneller als Win32 ReadFile() Zugang? Ich würde erwarten, dass raw-Win32-APIs zu haben weniger Aufwand als CRT. Was vermisse ich hier?

Kompilierbare testen von C++ - source-code folgt.

---

BEARBEITEN

Ich wiederholte die tests mit 4KB lese-Puffer und mit drei verschiedenen Dateien (mit gleichem Inhalt) zu vermeiden caching Effekte verfälschen können performance-Messungen, und nun die Ergebnisse wie erwartet sind.

Zum Beispiel, für eine Datei von circa 400 MB hier sind die Ergebnisse:

1. Win32 memory mapping: 305.908 ms

2. Win32-Datei (CreateFile): 451.402 ms

3. C-Datei (FILE*): 460.579 ms

---

////////////////////////////////////////////////////////////////////////////////
//Test file reading using C FILE*, Win32 CreateFile and Win32 memory mapping.
////////////////////////////////////////////////////////////////////////////////


#include <stdio.h>
#include <stdlib.h>
#include <algorithm>
#include <exception>
#include <iostream>
#include <stdexcept>
#include <vector>
#include <Windows.h>


//------------------------------------------------------------------------
//                     Performance (speed) measurement
//------------------------------------------------------------------------

long long counter()
{
    LARGE_INTEGER li;
    QueryPerformanceCounter(&li);
    return li.QuadPart;
}

long long frequency()
{
    LARGE_INTEGER li;
    QueryPerformanceFrequency(&li);
    return li.QuadPart;
}

void print_time(const long long start, const long long finish,
    const char * const s)
{
    std::cout << s << ": " << (finish - start) * 1000.0 / frequency() << " ms\n";
}


//------------------------------------------------------------------------
//                     RAII handle wrappers
//------------------------------------------------------------------------

struct c_file_traits
{
    typedef FILE* type;

    static FILE* invalid_value()
    {
        return nullptr;
    }

    static void close(FILE* f)
    {
        fclose(f);
    }
};

struct win32_file_traits
{
    typedef HANDLE type;

    static HANDLE invalid_value()
    {
        return INVALID_HANDLE_VALUE;
    }

    static void close(HANDLE h)
    {
        CloseHandle(h);
    }
};

struct win32_handle_traits
{
    typedef HANDLE type;

    static HANDLE invalid_value()
    {
        return nullptr;
    }

    static void close(HANDLE h)
    {
        CloseHandle(h);
    }
};

template <typename Traits>
class handle
{
public:
    typedef typename Traits::type type;

    handle()
        : _h(Traits::invalid_value())
    {
    }

    explicit handle(type h)
        : _h(h)
    {
    }

    ~handle()
    {
        close();
    }

    bool valid() const
    {
        return (_h != Traits::invalid_value());
    }

    type get() const
    {
        return _h;
    }

    void close()
    {
        if (valid())
            Traits::close(_h);

        _h = Traits::invalid_value();
    }

    void reset(type h)
    {
        if (h != _h)
        {
            close();
            _h = h;
        }
    }


private: //Ban copy
    handle(const handle&);
    handle& operator=(const handle&);

private:
    type _h;    //wrapped raw handle
};

typedef handle<c_file_traits> c_file_handle;
typedef handle<win32_file_traits> win32_file_handle;
typedef handle<win32_handle_traits> win32_handle;


//------------------------------------------------------------------------
//             File reading tests using various techniques
//------------------------------------------------------------------------

unsigned long long count_char_using_c_file(const std::string& filename, const char ch)
{
    unsigned long long char_count = 0;

#pragma warning(push)
#pragma warning(disable: 4996) //fopen use is OK
    c_file_handle file(fopen(filename.c_str(), "rb"));
#pragma warning(pop)

    if (!file.valid())
        throw std::runtime_error("Can't open file.");

    std::vector<char> read_buffer(4*1024); //4 KB
    bool has_more_data = true;
    while (has_more_data)
    {
        size_t read_count = fread(read_buffer.data(), 1, read_buffer.size(), file.get());
        for (size_t i = 0; i < read_count; i++)
        {
            if (read_buffer[i] == ch)
                char_count++;
        }

        if (read_count < read_buffer.size())
            has_more_data = false;
    }

    return char_count;
}


unsigned long long count_char_using_win32_file(const std::string& filename, const char ch)
{
    unsigned long long char_count = 0;

    win32_file_handle file(::CreateFileA(
        filename.c_str(),
        GENERIC_READ,
        FILE_SHARE_READ,
        nullptr,
        OPEN_EXISTING,
        FILE_FLAG_SEQUENTIAL_SCAN,
        nullptr
        )
        );
    if (!file.valid())
        throw std::runtime_error("Can't open file.");

    std::vector<char> read_buffer(4*1024); //4 KB
    bool has_more_data = true;
    while (has_more_data)
    {
        DWORD read_count = 0;
        if (!ReadFile(file.get(), read_buffer.data(), read_buffer.size(), &read_count, nullptr))
            throw std::runtime_error("File read error using ReadFile().");

        for (size_t i = 0; i < read_count; i++)
        {
            if (read_buffer[i] == ch)
                char_count++;
        }

        if (read_count < sizeof(read_buffer))
            has_more_data = false;
    }

    return char_count;
}


//Memory-map a file.
class file_map
{
public:
    explicit file_map(const std::string& filename)
        : _view(nullptr), _length(0)
    {
        _file.reset(::CreateFileA(
            filename.c_str(),
            GENERIC_READ,
            FILE_SHARE_READ,
            nullptr,
            OPEN_EXISTING,
            FILE_ATTRIBUTE_NORMAL,
            nullptr));
        if (!_file.valid())
            return;

        LARGE_INTEGER file_size;
        if (!GetFileSizeEx(_file.get(), &file_size))
            return;

        if (file_size.QuadPart == 0)
            return;

        _mapping.reset(::CreateFileMapping(
            _file.get(), nullptr,
            PAGE_READONLY,
            0,
            0,
            nullptr)
            );
        if (!_mapping.valid())
            return;

        _view = reinterpret_cast<char*>
            (::MapViewOfFile(_mapping.get(), FILE_MAP_READ, 0, 0, 0));
        if (!_view)
            return;

        _length = file_size.QuadPart;
    }

    ~file_map()
    {
        if (_view)
            UnmapViewOfFile(_view);
    }

    bool valid() const
    {
        return (_view != nullptr);
    }

    const char * begin() const
    {
        return _view;
    }

    const char * end() const
    {
        return begin() + length();
    }

    unsigned long long length() const
    {
        return _length;
    }

private:    //ban copy
    file_map(const file_map&);
    file_map& operator=(const file_map&);

private:
    win32_file_handle   _file;
    win32_handle        _mapping;
    char*               _view;
    unsigned long long  _length;    //in bytes
};


unsigned long long count_char_using_memory_mapping(const std::string& filename, const char ch)
{
    unsigned long long char_count = 0;

    file_map view(filename);
    if (!view.valid())
        throw std::runtime_error("Can't create memory-mapping of file.");

    for (auto it = view.begin(); it != view.end(); ++it)
    {
        if (*it == ch)
        {
            char_count++;
        }
    }

    return char_count;
}


template <typename TestFunc>
void run_test(const char * message, TestFunc test, const std::string& filename, const char ch)
{
    const long long start = counter();
    const unsigned long long char_count = test(filename, ch);
    const long long finish = counter();
    print_time(start, finish, message);
    std::cout << "Count of \'" << ch << "\' : " << char_count << "\n\n";
}


int main(int argc, char* argv[])
{
    static const int kExitOk = 0;
    static const int kExitError = 1;

    if (argc != 3)
    {
        std::cerr << argv[0] << " <char> <filename>.\n";
        std::cerr << "Counts occurrences of ASCII character <char>\n";
        std::cerr << "in the <filename> file.\n\n";
        return kExitError;
    }

    const char ch = *(argv[1]);
    const std::string filename = argv[2];

    try
    {
        //Execute tests on THREE different files with the same content,
        //to avoid caching effects.
        //(file names have incremental number suffix).
        run_test("C <stdio.h> file (FILE*)", count_char_using_c_file, filename + "1", ch);
        run_test("Win32 file (CreateFile)", count_char_using_win32_file, filename + "2", ch);
        run_test("Win32 memory mapping", count_char_using_memory_mapping, filename + "3", ch);

        return kExitOk;
    }
    catch (const std::exception& e)
    {
        std::cerr << "\n*** ERROR: " << e.what() << '\n';
        return kExitError;
    }
}

////////////////////////////////////////////////////////////////////////////////