Question

我遇到串行流超出4GB限制的问题，即使它运行在具有足够内存的64位Linux机箱上。

下面的测试代码（读完你的评论后修改）4GB之后的核心转储。

在gdb跟踪中，stringstream使用默认的std :: char_traits，其中int_type设置为32bit int，而不是64bit size_t。有什么建议可以解决吗？

#include <stdint.h>
#include <iostream>
#include <sstream>
#include <math.h>
using namespace std;

int main(int narg, char** argv)
{
    string str;
    stringstream ss;
    const size_t GB = (size_t)pow(2, 30);

    str.resize(GB, '1');
    cerr << "1GB=" << str.size()
             << ", string::max_size=" << str.max_size()/GB << "GB"
             << ", sizeof(int)=" << sizeof(int)
             << ", sizeof(int64_t)=" << sizeof(int64_t)
             << ", sizeof(size_t)=" << sizeof(size_t)
             << endl;
    string().swap(str);

    str.resize(6*GB, '6');
    cerr << "str.size()=" << (str.size() / GB) << "GB allocated successfully"
            << ", ended with " << str.substr(str.size()-5, 5) << endl;
    string().swap(str);

    str.resize(GB/4, 'Q');
    cerr << "writing to stringstream..." << std::flush;
    for (int i = 0; i < 30; ++i) {
        ss << str << endl;
        cerr << double(ss.str().size())/GB << "GB " << std::flush;
    }
    cerr << endl;
    exit(0);
}

输出结果为：

1GB=1073741824, string::max_size=4294967295GB, sizeof(int)=4, sizeof(int64_t)=8, sizeof(size_t)=8
str.size()=6GB allocated successfully, ended with 66666
writing to stringstream...0.25GB 0.5GB 0.75GB 1GB 1.25GB 1.5GB 1.75GB 2GB 2.25GB 2.5GB 2.75GB 3GB 3.25GB 3.5GB 3.75GB Segmentation fault (core dumped)

gdb堆栈跟踪是：

(gdb) where
#0  0x00002aaaaad5e0c1 in std::basic_stringbuf<char, std::char_traits<char>, std::allocator<char> >::overflow(int) () from /usr/lib64/libstdc++.so.6
#1  0x00002aaaaad62cbd in std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long) () from /usr/lib64/libstdc++.so.6
#2  0x00002aaaaad5657d in std::basic_ostream<char, std::char_traits<char> >& std::operator<< <char, std::char_traits<char>, std::allocator<char> >(std::basic_ostream<char, std::char_traits<char> >&, std::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) () from /usr/lib64/libstdc++.so.6
#3  0x000000000040112b in main ()

二进制文件似乎是64位。

$ file a.out
a.out: ELF 64-bit LSB executable, AMD x86-64, version 1 (SYSV), for GNU/Linux 2.6.9, dynamically linked (uses shared libs), for GNU/Linux 2.6.9, not stripped

Nick，检查预处理器输出的好点。某种程度上std :: char_straits会覆盖__gnu_cxx :: char_straits，并将int_type重新定义为int，而不是像__gnu_cxx :: char_straits那样重新定义无符号长整数。这非常令人惊讶！

namespace __gnu_cxx
{
# 61 "/usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/char_traits.h" 3
  template <class _CharT>
    struct _Char_types
    {
      typedef unsigned long int_type;
      typedef std::streampos pos_type;
      typedef std::streamoff off_type;
      typedef std::mbstate_t state_type;
    };
# 86 "/usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/char_traits.h" 3
  template<typename _CharT>
    struct char_traits
    {
      typedef _CharT char_type;
      typedef typename _Char_types<_CharT>::int_type int_type;
      typedef typename _Char_types<_CharT>::pos_type pos_type;
      typedef typename _Char_types<_CharT>::off_type off_type;
      typedef typename _Char_types<_CharT>::state_type state_type;
              ....
               };

namespace std
{
# 224 "/usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/char_traits.h" 3
  template<class _CharT>
    struct char_traits : public __gnu_cxx::char_traits<_CharT>
    { };



  template<>
    struct char_traits<char>
    {
      typedef char char_type;
      typedef int int_type;
      typedef streampos pos_type;
      typedef streamoff off_type;
      typedef mbstate_t state_type;
              ...
              };

编辑：以下来自STL网站http://www.cplusplus.com/reference/string/char_traits/，其中char_traits专业化使用int。

typedef INT_T int_type; 
Where INT_T is a type that can represent all the valid characters representable by a    char_type plus an end-of-file value (eof) which is compatible with iostream class member functions.
For char_traits<char> this is int, and for char_traits<wchar_t> this is wint_t

Answer 1

您可以发布预处理的源文件。

已移除对_Char_types的引用，因为它具有误导性。

我不确定int_type是否相关，char的特化确实对int_type使用了int。

int_type是一个用于保存单个字符的typedef（即ascii至少为一个字节，wchar_t为更高字节）。它不用于存储一系列字符（请参阅下面的std :: streamoff）。

从你的预处理输出我怀疑std :: streamoff可能是罪魁祸首。从我系统的标题：

# 90 "/usr/include/c++/4.6/bits/postypes.h" 3
  typedef long streamoff;

std :: streamoff用于std :: streampos，如果定义不正确，我认为会导致stringstream调用溢出函数。

您是否检查过包含了正确的标题？

# 61 "/usr/lib/gcc/x86_64-redhat-linux/4.1.2/../../../../include/c++/4.1.2/bits/char_traits.h" 3

是以下路径：

/usr/include/c++/4.1.2/bits/char_traits.h

-nick

stringstream溢出4GB

1 个答案: