以理智、安全、高效的方式复制文件

我寻找一种复制文件（二进制或文本）的好方法。我已经写了几个示例，每个人都可以工作。但我想听听经验丰富的程序员的意见。

我缺少好的例子并寻找一种与 C++ 一起使用的方法。

ANSI-C-WAY

#include <iostream>
#include <cstdio>    // fopen, fclose, fread, fwrite, BUFSIZ
#include <ctime>
using namespace std;

int main() {
    clock_t start, end;
    start = clock();

    // BUFSIZE default is 8192 bytes
    // BUFSIZE of 1 means one chareter at time
    // good values should fit to blocksize, like 1024 or 4096
    // higher values reduce number of system calls
    // size_t BUFFER_SIZE = 4096;

    char buf[BUFSIZ];
    size_t size;

    FILE* source = fopen("from.ogv", "rb");
    FILE* dest = fopen("to.ogv", "wb");

    // clean and more secure
    // feof(FILE* stream) returns non-zero if the end of file indicator for stream is set

    while (size = fread(buf, 1, BUFSIZ, source)) {
        fwrite(buf, 1, size, dest);
    }

    fclose(source);
    fclose(dest);

    end = clock();

    cout << "CLOCKS_PER_SEC " << CLOCKS_PER_SEC << "\n";
    cout << "CPU-TIME START " << start << "\n";
    cout << "CPU-TIME END " << end << "\n";
    cout << "CPU-TIME END - START " << end - start << "\n";
    cout << "TIME(SEC) " << static_cast<double>(end - start) / CLOCKS_PER_SEC << "\n";

    return 0;
}

POSIX-WAY（K&R 在《C 编程语言》中使用了这个，更底层）

#include <iostream>
#include <fcntl.h>   // open
#include <unistd.h>  // read, write, close
#include <cstdio>    // BUFSIZ
#include <ctime>
using namespace std;

int main() {
    clock_t start, end;
    start = clock();

    // BUFSIZE defaults to 8192
    // BUFSIZE of 1 means one chareter at time
    // good values should fit to blocksize, like 1024 or 4096
    // higher values reduce number of system calls
    // size_t BUFFER_SIZE = 4096;

    char buf[BUFSIZ];
    size_t size;

    int source = open("from.ogv", O_RDONLY, 0);
    int dest = open("to.ogv", O_WRONLY | O_CREAT /*| O_TRUNC/**/, 0644);

    while ((size = read(source, buf, BUFSIZ)) > 0) {
        write(dest, buf, size);
    }

    close(source);
    close(dest);

    end = clock();

    cout << "CLOCKS_PER_SEC " << CLOCKS_PER_SEC << "\n";
    cout << "CPU-TIME START " << start << "\n";
    cout << "CPU-TIME END " << end << "\n";
    cout << "CPU-TIME END - START " << end - start << "\n";
    cout << "TIME(SEC) " << static_cast<double>(end - start) / CLOCKS_PER_SEC << "\n";

    return 0;
}

KISS-C++-Streambuffer-WAY

#include <iostream>
#include <fstream>
#include <ctime>
using namespace std;

int main() {
    clock_t start, end;
    start = clock();

    ifstream source("from.ogv", ios::binary);
    ofstream dest("to.ogv", ios::binary);

    dest << source.rdbuf();

    source.close();
    dest.close();

    end = clock();

    cout << "CLOCKS_PER_SEC " << CLOCKS_PER_SEC << "\n";
    cout << "CPU-TIME START " << start << "\n";
    cout << "CPU-TIME END " << end << "\n";
    cout << "CPU-TIME END - START " <<  end - start << "\n";
    cout << "TIME(SEC) " << static_cast<double>(end - start) / CLOCKS_PER_SEC << "\n";

    return 0;
}

复制算法-C++-WAY

#include <iostream>
#include <fstream>
#include <ctime>
#include <algorithm>
#include <iterator>
using namespace std;

int main() {
    clock_t start, end;
    start = clock();

    ifstream source("from.ogv", ios::binary);
    ofstream dest("to.ogv", ios::binary);

    istreambuf_iterator<char> begin_source(source);
    istreambuf_iterator<char> end_source;
    ostreambuf_iterator<char> begin_dest(dest); 
    copy(begin_source, end_source, begin_dest);

    source.close();
    dest.close();

    end = clock();

    cout << "CLOCKS_PER_SEC " << CLOCKS_PER_SEC << "\n";
    cout << "CPU-TIME START " << start << "\n";
    cout << "CPU-TIME END " << end << "\n";
    cout << "CPU-TIME END - START " <<  end - start << "\n";
    cout << "TIME(SEC) " << static_cast<double>(end - start) / CLOCKS_PER_SEC << "\n";

    return 0;
}

自己的缓冲区 C++ 方式

#include <iostream>
#include <fstream>
#include <ctime>
using namespace std;

int main() {
    clock_t start, end;
    start = clock();

    ifstream source("from.ogv", ios::binary);
    ofstream dest("to.ogv", ios::binary);

    // file size
    source.seekg(0, ios::end);
    ifstream::pos_type size = source.tellg();
    source.seekg(0);
    // allocate memory for buffer
    char* buffer = new char[size];

    // copy file    
    source.read(buffer, size);
    dest.write(buffer, size);

    // clean up
    delete[] buffer;
    source.close();
    dest.close();

    end = clock();

    cout << "CLOCKS_PER_SEC " << CLOCKS_PER_SEC << "\n";
    cout << "CPU-TIME START " << start << "\n";
    cout << "CPU-TIME END " << end << "\n";
    cout << "CPU-TIME END - START " <<  end - start << "\n";
    cout << "TIME(SEC) " << static_cast<double>(end - start) / CLOCKS_PER_SEC << "\n";

    return 0;
}

Linux-WAY// 需要内核 >= 2.6.33

#include <iostream>
#include <sys/sendfile.h>  // sendfile
#include <fcntl.h>         // open
#include <unistd.h>        // close
#include <sys/stat.h>      // fstat
#include <sys/types.h>     // fstat
#include <ctime>
using namespace std;

int main() {
    clock_t start, end;
    start = clock();

    int source = open("from.ogv", O_RDONLY, 0);
    int dest = open("to.ogv", O_WRONLY | O_CREAT /*| O_TRUNC/**/, 0644);

    // struct required, rationale: function stat() exists also
    struct stat stat_source;
    fstat(source, &stat_source);

    sendfile(dest, source, 0, stat_source.st_size);

    close(source);
    close(dest);

    end = clock();

    cout << "CLOCKS_PER_SEC " << CLOCKS_PER_SEC << "\n";
    cout << "CPU-TIME START " << start << "\n";
    cout << "CPU-TIME END " << end << "\n";
    cout << "CPU-TIME END - START " <<  end - start << "\n";
    cout << "TIME(SEC) " << static_cast<double>(end - start) / CLOCKS_PER_SEC << "\n";

    return 0;
}

环境

• GNU/LINUX (Archlinux)
• 内核3.3
• GLIBC-2.15、LIBSTDC++ 4.7（GCC-LIBS）、GCC 4.7、Coreutils 8.16
• 使用 RUNLEVEL 3（多用户、网络、终端、无 GUI）
• INTEL SSD-Postville 80 GB，已满 50%
• 复制 270 MB OGG 视频文件

重现步骤

 1. $ rm from.ogg
 2. $ reboot                           # kernel and filesystem buffers are in regular
 3. $ (time ./program) &>> report.txt  # executes program, redirects output of program and append to file
 4. $ sha256sum *.ogv                  # checksum
 5. $ rm to.ogg                        # remove copy, but no sync, kernel and fileystem buffers are used
 6. $ (time ./program) &>> report.txt  # executes program, redirects output of program and append to file

结果（使用的 CPU 时间）

Program  Description                 UNBUFFERED|BUFFERED
ANSI C   (fread/frwite)                 490,000|260,000  
POSIX    (K&R, read/write)              450,000|230,000  
FSTREAM  (KISS, Streambuffer)           500,000|270,000 
FSTREAM  (Algorithm, copy)              500,000|270,000
FSTREAM  (OWN-BUFFER)                   500,000|340,000  
SENDFILE (native LINUX, sendfile)       410,000|200,000  

文件大小不变。
sha256sum 打印相同的结果。
视频文件仍然可以播放。

问题

• 您更喜欢哪种方法？
• 您知道更好的解决方案吗？
• 你看到我的代码有什么错误吗？

• 您知道避免解决方案的原因吗？

• FSTREAM（KISS、流缓冲区）
  我真的很喜欢这个，因为它真的很短而且简单。据我所知，运算符

Thanks

Update 1
我以这种方式更改了所有示例中的源，文件描述符的打开和关闭包含在测量中clock()。它们的源代码没有其他重大变化。结果没有改变！我也用过time仔细检查我的结果。

Update 2
ANSI C 示例已更改：条件while循环不再打电话feof()相反，我搬家了fread()进入状态。看起来，代码现在运行速度快了 10,000 个时钟。

测量改变：以前的结果总是被缓冲，因为我重复了旧的命令行rm to.ogv && 同步 && 时间 ./program每个程序几次。现在我为每个程序重新启动系统。未缓冲的结果是新的，并不令人意外。未缓冲的结果并没有真正改变。

如果我不删除旧副本，程序的反应会有所不同。覆盖现有文件bufferedPOSIX 和 SENDFILE 速度更快，所有其他程序都较慢。也许选项truncate or create对此行为有影响。但用相同的副本覆盖现有文件并不是现实世界的用例。

执行复制cp无缓冲需要 0.44 秒，缓冲需要 0.30 秒。所以cp比 POSIX 示例慢一点。对我来说看起来不错。

也许我还添加了样本和结果mmap() and copy_file()来自 boost::文件系统。

Update 3
我也将其放在博客页面上并对其进行了一些扩展。包括splice()，这是 Linux 内核的一个低级函数。也许接下来会出现更多使用 Java 的示例。http://www.ttyhoney.com/blog/?page_id=69 http://www.ttyhoney.com/blog/?page_id=69

以合理的方式复制文件：

#include <fstream>

int main()
{
    std::ifstream  src("from.ogv", std::ios::binary);
    std::ofstream  dst("to.ogv",   std::ios::binary);

    dst << src.rdbuf();
}

这本书读起来非常简单直观，值得额外付费。如果我们经常这样做，最好依靠操作系统对文件系统的调用。我相信boost在其文件系统类中有一个复制文件方法。

有一种与文件系统交互的 C 方法：

#include <copyfile.h>

int
copyfile(const char *from, const char *to, copyfile_state_t state, copyfile_flags_t flags);