c++ - 运行多线程时双重释放或损坏

Question

我在调用可靠库 ANN 并使用 OpenMP 并行化 for 循环的 C++ 程序中遇到运行时错误“双重释放或损坏”。

*** glibc detected *** /home/tim/test/debug/test: double free or corruption (!prev): 0x0000000002527260 ***     

是否意味着地址0x0000000002527260处的内存被释放了不止一次？

错误发生在“_search_struct->annkSearch(queryPt, k_max, nnIdx, dists, _eps);”在函数 classify_various_k() 中，它又在函数 tune_complexity() 中的 OpenMP for 循环中。

请注意，当 OpenMP 有多个线程时会发生此错误，而在单线程情况下不会发生。不知道为什么。

以下是我的代码。如果这还不足以诊断，请告诉我。感谢您的帮助!

  void KNNClassifier::train(int nb_examples, int dim, double **features, int * labels) {                         
      _nPts = nb_examples;  

      _labels = labels;  
      _dataPts = features;  

      setting_ANN(_dist_type,1);   

    delete _search_struct;  
    if(strcmp(_search_neighbors, "brutal") == 0) {                                                                 
      _search_struct = new ANNbruteForce(_dataPts, _nPts, dim);  
    }else if(strcmp(_search_neighbors, "kdtree") == 0) {  
      _search_struct = new ANNkd_tree(_dataPts, _nPts, dim);  
      }  

  }  


      void KNNClassifier::classify_various_k(int dim, double *feature, int label, int *ks, double * errors, int nb_ks, int k_max) {            
        ANNpoint      queryPt = 0;                                                                                                                
        ANNidxArray   nnIdx = 0;                                                                                                         
        ANNdistArray  dists = 0;                                                                                                         

        queryPt = feature;     
        nnIdx = new ANNidx[k_max];                                                               
        dists = new ANNdist[k_max];                                                                                

        if(strcmp(_search_neighbors, "brutal") == 0) {                                                                               
          _search_struct->annkSearch(queryPt, k_max,  nnIdx, dists, _eps);    
        }else if(strcmp(_search_neighbors, "kdtree") == 0) {    
          _search_struct->annkSearch(queryPt, k_max,  nnIdx, dists, _eps); // where error occurs    
        }    

        for (int j = 0; j < nb_ks; j++)    
        {    
          scalar_t result = 0.0;    
          for (int i = 0; i < ks[j]; i++) {                                                                                      
              result+=_labels[ nnIdx[i] ];    
          }    
          if (result*label<0) errors[j]++;    
        }    

        delete [] nnIdx;    
        delete [] dists;    

      }    

      void KNNClassifier::tune_complexity(int nb_examples, int dim, double **features, int *labels, int fold, char *method, int nb_examples_test, double **features_test, int *labels_test) {    
          int nb_try = (_k_max - _k_min) / scalar_t(_k_step);    
          scalar_t *error_validation = new scalar_t [nb_try];    
          int *ks = new int [nb_try];    

          for(int i=0; i < nb_try; i ++){    
            ks[i] = _k_min + _k_step * i;    
          }    

          if (strcmp(method, "ct")==0)                                                                                                                     
          {    

            train(nb_examples, dim, features, labels );// train once for all nb of nbs in ks                                                                                                

            for(int i=0; i < nb_try; i ++){    
              if (ks[i] > nb_examples){nb_try=i; break;}    
              error_validation[i] = 0;    
            }    

            int i = 0;    
      #pragma omp parallel shared(nb_examples_test, error_validation,features_test, labels_test, nb_try, ks) private(i)    
            {    
      #pragma omp for schedule(dynamic) nowait    
              for (i=0; i < nb_examples_test; i++)         
              {    
                classify_various_k(dim, features_test[i], labels_test[i], ks, error_validation, nb_try, ks[nb_try - 1]); // where error occurs    
              }    
            }    
            for (i=0; i < nb_try; i++)    
            {    
              error_validation[i]/=nb_examples_test;    
            }    
          }

          ......
     }

---

更新:

谢谢!我现在正尝试通过使用“#pragma omp critical”来纠正在 classify_various_k() 中写入相同内存问题的冲突:

void KNNClassifier::classify_various_k(int dim, double *feature, int label, int *ks, double * errors, int nb_ks, int k_max) {   
  ANNpoint      queryPt = 0;    
  ANNidxArray   nnIdx = 0;      
  ANNdistArray  dists = 0;     

  queryPt = feature; //for (int i = 0; i < Vignette::size; i++){ queryPt[i] = vignette->content[i];}         
  nnIdx = new ANNidx[k_max];                
  dists = new ANNdist[k_max];               

  if(strcmp(_search_neighbors, "brutal") == 0) {// search  
    _search_struct->annkSearch(queryPt, k_max,  nnIdx, dists, _eps);  
  }else if(strcmp(_search_neighbors, "kdtree") == 0) {  
    _search_struct->annkSearch(queryPt, k_max,  nnIdx, dists, _eps);  
  }  

  for (int j = 0; j < nb_ks; j++)  
  {  
    scalar_t result = 0.0;  
    for (int i = 0; i < ks[j]; i++) {          
        result+=_labels[ nnIdx[i] ];  // Program received signal SIGSEGV, Segmentation fault
    }  
    if (result*label<0)  
    {  
    #pragma omp critical  
    {  
      errors[j]++;  
    }  
    }  

  }  

  delete [] nnIdx;  
  delete [] dists;  

}

但是，在“result+=_labels[ nnIdx[i] ];”处有一个新的段错误错误。一些想法？谢谢!

Answer 1

好的，既然您已经声明它在单线程情况下可以正常工作，那么“正常”方法将不起作用。您需要执行以下操作:

• 找到并行访问的所有变量
• 特别是看看那些修改过的
• 不要对共享资源调用 delete
• 查看所有对共享资源进行操作的库函数 - 检查它们是否不进行分配/解除分配

这是被双重删除的候选人列表:

shared(nb_examples_test, error_validation,features_test, labels_test, nb_try, ks)

另外，这段代码可能不是线程安全的:

      for (int i = 0; i < ks[j]; i++) {
         result+=_labels[ nnIdx[i] ]; 
      }    
      if (result*label<0) errors[j]++;  

因为两个或多个进程可能会尝试写入错误数组。

还有一个重要建议——尽量不要在线程模式下访问(尤其是修改!)任何东西，那不是函数的参数!