【发布时间】：2012-04-29 00:50:57
【问题描述】：
我正在寻找一种复制文件（二进制或文本）的好方法。我写了几个样本，每个人都工作。但我想听听经验丰富的程序员的意见。
我错过了很好的例子并寻找一种适用于 C++ 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”中使用它，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;
}
COPY-ALGORITHM-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;
}
OWN-BUFFER-C++-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);
// 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，最多填充 50%
- 复制 270 MB OGG-VIDEO-FILE
复制步骤
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
文件大小不会改变。
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？
- 您是否发现我的代码中有任何错误？
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，因为它真的很短很简单。据我所知，运算符
谢谢
更新 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 clock() 的测量中。它们在源代码中没有其他重大变化。结果没变！我还使用 time 来仔细检查我的结果。
更新 2
ANSI C 示例更改：while-loop 的条件不再调用 feof() 而是我将 fread() 移到健康）状况。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，因为我对每个程序重复了几次旧的命令行rm to.ogv && sync && time ./program。现在我为每个程序重新启动系统。无缓冲的结果是新的，并不令人惊讶。无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。使用 POSIX 和 SENDFILE 覆盖现有文件 缓冲 更快，所有其他程序都更慢。也许选项 truncate 或 create 对此行为有影响。但是用相同的副本覆盖现有文件并不是现实世界的用例。
使用 cp 执行复制需要 0.44 秒无缓冲和 0.30 秒缓冲。所以 cp 比 POSIX 示例慢一点。对我来说看起来不错。
也许我还添加了来自 boost::filesystem 的 mmap() 和 copy_file() 的样本和结果。
更新 3
我也把它放在了一个博客页面上，并对其进行了一些扩展。包括 splice()，这是一个来自 Linux 内核的低级函数。也许会有更多的 Java 示例。
http://www.ttyhoney.com/blog/?page_id=69
【问题讨论】：
-
fstream绝对是文件操作的好选择。 -
你忘了偷懒方式：system("cp from.ogv to.ogv");
-
#include <copyfile.h> copyfile(const char *from, const char *to, copyfile_state_t state, copyfile_flags_t flags); -
很抱歉这么晚才加入，但我认为这些都不是“安全的”，因为它们没有任何错误处理。