控制台文本输出速度对比，结果让人无语。

大至以前也使用过C#，当时在垃圾的机器上运行控制台的输出程序，除了程序启运瞬间比较慢的话，感觉中间的输出可是比C的printf， puts快了很多，当时觉得挺神奇的，还以为是语言的不同造成的，结果无意中的这个测试，解释了心中的疑惑。Java底层其实也是直接调用Win32 API，不过由于本身语言的效率，感觉没有C#明显。
如果不考虑同步问题，我们得到的结果依然是C++的cout执行最慢。puts的效率，从mscrt源代码上来看，puts是调用_fwrite_lk 这个函数实现的，看着这么长的一段代码，能快多少？
/* define the normal version */
#ifdef _MT
size_t __cdecl _fwrite_lk (
#else /* _MT */
size_t __cdecl fwrite (
#endif /* _MT */
const void *buffer,
size_t size,
size_t num,
FILE *stream
)
{
const char *data; /* point to where data comes from next */
unsigned total; /* total bytes to write */
unsigned count; /* num bytes left to write */
unsigned bufsize; /* size of stream buffer */
unsigned nbytes; /* number of bytes to write now */
unsigned nwritten; /* number of bytes written */
int c; /* a temp char */
/* initialize local vars */
data = buffer;
count = total = size * num;
if (0 == count)
return 0;
if (anybuf(stream))
/* already has buffer, use its size */
bufsize = stream->_bufsiz;
else
#if defined (_M_M68K) || defined (_M_MPPC)
/* assume will get BUFSIZ buffer */
bufsize = BUFSIZ;
#else /* defined (_M_M68K) || defined (_M_MPPC) */
/* assume will get _INTERNAL_BUFSIZ buffer */
bufsize = _INTERNAL_BUFSIZ;
#endif /* defined (_M_M68K) || defined (_M_MPPC) */
/* here is the main loop -- we go through here until we're done */
while (count != 0) {
/* if the buffer is big and has room, copy data to buffer */
if (bigbuf(stream) && stream->_cnt != 0) {
/* how much do we want? */
nbytes = (count < (unsigned)stream->_cnt) ? count : stream->_cnt;
memcpy(stream->_ptr, data, nbytes);
/* update stream and amt of data written */
count -= nbytes;
stream->_cnt -= nbytes;
stream->_ptr += nbytes;
data += nbytes;
}
else if (count >= bufsize) {
/* If we have more than bufsize chars to write, write
data by calling write with an integral number of
bufsiz blocks. If we reach here and we have a big
buffer, it must be full so _flush it. */
if (bigbuf(stream)) {
if (_flush(stream)) {
/* error, stream flags set -- we're out
of here */
return (total - count) / size;
}
}
/* calc chars to read -- (count/bufsize) * bufsize */
nbytes = ( bufsize ? (count - count % bufsize) :
count );
nwritten = _write(_fileno(stream), data, nbytes);
if (nwritten == (unsigned)EOF) {
/* error -- out of here */
stream->_flag |= _IOERR;
return (total - count) / size;
}
/* update count and data to reflect write */
count -= nwritten;
data += nwritten;
if (nwritten < nbytes) {
/* error -- out of here */
stream->_flag |= _IOERR;
return (total - count) / size;
}
}
else {
/* buffer full and not enough chars to do direct write,
so do a _flsbuf. */
c = *data; /* _flsbuf write one char, this is it */
if (_flsbuf(c, stream) == EOF) {
/* error or eof, stream flags set by _flsbuf */
return (total - count) / size;
}
/* _flsbuf wrote a char -- update count */
++data;
--count;
/* update buffer size */
bufsize = stream->_bufsiz > 0 ? stream->_bufsiz : 1;
}
}
/* we finished successfully, so just return num */
return num;
}
printf内部也是经过多次调用，只是打印字符串的话，实际只是执行了下面类似的代码，然后再执行puts，哈哈，基本上能想到想应的结果。
while(*fmt)
{
if(*fmt != 0x25)//%
{
this->push_back(*fmt++);
continue;
}