c++ - 使用共享变量的线程

Question

我尝试使用多个线程插入一个 boost::bimap .我在线程之间有一些共享变量，我需要通过引用传递它们，其中一些在每个线程执行时都会被修改。但是，我收到错误:

Segmentation fault (core dumped)

我有以下代码。我试图通过使用 std::lock_guard<std::mutex> lock(mtx) 来避免对变量的并发访问。 , 但无法使其工作。

parallel_index.cpp

#include <iostream>
#include <string>
#include <algorithm>
#include <thread>
#include <mutex>
#include <boost/bimap.hpp>
#include <boost/bimap/unordered_set_of.hpp>
#include <boost/bimap/unordered_multiset_of.hpp>
#include "parallel_index.h"


namespace bimaps = boost::bimaps;
typedef boost::bimap<bimaps::unordered_set_of<uint64_t>,
        bimaps::unordered_multiset_of<std::string> > bimap_reference;
typedef bimap_reference::value_type position;
bimap_reference reference_index_vector;


size_t total_threads = std::thread::hardware_concurrency();

std::string sequence_content = "ABCDDBACDDDCBBAAACBDAADCBDAAADCBDADADACBDDCBBBCDCBCDAADCBBCDAAADCBDA";
uint64_t sequence_length = sequence_content.length();
int split = 5;
uint64_t erase_length = 0;
unsigned int seq_itr = 0;

std::mutex mtx;   // to protect against concurent access
int main(){
    thread_test::create_index index;
    std::thread threads[total_threads];
    std::cout << total_threads <<  " threads lanched" << std::endl;
    for(unsigned int i = 0; i < total_threads; i++){
        threads[i] = std::thread(&thread_test::create_index::reference_index_hash, index,
                std::ref(sequence_length), std::ref(split), std::ref(sequence_content), std::ref(erase_length));
    }

    for(unsigned int i = 0; i < total_threads; i++){
        threads[i].join();
    }
}



/*
 * Creating index
 */
void thread_test::create_index::reference_index_hash(uint64_t &sequence_length, int &split,
        std::string &sequence_content, uint64_t &erase_length  ){

    for (; seq_itr < sequence_length; ++seq_itr ){

        std::lock_guard<std::mutex> lock(mtx);    
        std::string splitstr = sequence_content.substr(erase_length, split);
        reference_index_vector.insert(position(seq_itr, splitstr));
        seq_itr += split-1;
        erase_length += split;

        if(erase_length > 10000){
            sequence_content.erase(0,erase_length);
            erase_length = 0;
        }
    }


    for( bimap_reference::const_iterator iter = reference_index_vector.begin(), iend = reference_index_vector.end();
            iter != iend; ++iter ) {
        std::cout << iter->left << " <--> "<< iter->right <<std::endl;
    }


}

parallel_index.h

#ifndef PARALLEL_INDEX_H_
#define PARALLEL_INDEX_H_


#include<iostream>
#include <algorithm>
#include <utility>
#include <boost/bimap.hpp>
#include <boost/bimap/unordered_set_of.hpp>
#include <boost/bimap/unordered_multiset_of.hpp>




//typedef boost::unordered_map<int, std::pair<int, unsigned long int>& > reference_map;

namespace bimaps = boost::bimaps;

typedef boost::bimap<bimaps::unordered_set_of<uint64_t>,
        bimaps::unordered_multiset_of<std::string > > bimap_reference;
typedef bimap_reference::value_type position;
extern bimap_reference reference_index_vector;


namespace thread_test{

class create_index{
public:
    void reference_index_hash(uint64_t &sequence_length, int &split,
            std::string &sequence_content, uint64_t &erase_length);
};
}


#endif /* PARALLEL_INDEX_H_ */

----------------------------编辑------------ ----------------------

我尝试将字符串内容划分为与线程数相等的分区，以使每个线程在本地可用。但似乎没有任何效果。有时它会完成第一个线程并在 Segmentation fault (core dumped) 之后停在那里.

parallel_index.cpp

#include <iostream>
#include <string>
#include <algorithm>
#include <thread>
#include <mutex>
#include <boost/bimap.hpp>
#include <boost/bimap/unordered_set_of.hpp>
#include <boost/bimap/unordered_multiset_of.hpp>
#include "parallel_index.h"


namespace bimaps = boost::bimaps;
typedef boost::bimap<bimaps::unordered_set_of<uint64_t>,
        bimaps::unordered_multiset_of<std::string> > bimap_reference;
typedef bimap_reference::value_type position;
bimap_reference reference_index_vector;


//create threads
size_t total_threads = std::thread::hardware_concurrency();


std::string sequence_content = "ABCDDBACDDDCBBAAACBDAADCBDAAADCBDADADACBDDCBBBCDCBCDAADCBBCDAAADCBDADDCCCAAABBBAAACDCA";
uint64_t sequence_length = sequence_content.length();
int split = 5;

// split the sequence_content equal to the number of threads, and assign each partition to each thread.
uint64_t each_partition_len = sequence_content.length()/total_threads- (sequence_content.length()/total_threads)%split ;
uint64_t last_partition_len = sequence_content.length()/total_threads +
        (((sequence_content.length()/total_threads)%split)*(total_threads-1)) + sequence_content.length()%total_threads;


std::mutex mtx;   // to protect against concurent access
int main(){
    thread_test::create_index index;
    std::thread threads[total_threads];

    std::cout << total_threads <<  " threads lanched" << std::endl;

    for(unsigned int i = 0; i < total_threads; i++){

        if(i < total_threads-1)
            threads[i] = std::thread(&thread_test::create_index::reference_index_hash, index,
                            std::ref(each_partition_len), std::ref(split), std::ref(sequence_content), i);

        else
            threads[i] = std::thread(&thread_test::create_index::reference_index_hash, index,
                                        std::ref(last_partition_len), std::ref(split), std::ref(sequence_content), i);

        //std::lock_guard<std::mutex> lck(mtx);
        std::cout << "launched thread " << i << "with id " << threads[i].get_id() << std::endl;
    }


    for( bimap_reference::const_iterator iter = reference_index_vector.begin(), iend = reference_index_vector.end();
            iter != iend; ++iter ) {
        std::cout << iter->left << " <--> "<< iter->right <<std::endl;
    }

    for( unsigned int i = 0; i < total_threads; ++i){
        if(threads[i].joinable()){
            std::cout << "trying to join thread " << i << std:: endl;
            threads[i].join();
            std::cout << "thread joined " << i << std:: endl;
        }
    }

    for( bimap_reference::const_iterator iter = reference_index_vector.begin(), iend = reference_index_vector.end();
            iter != iend; ++iter ) {
        std::cout << iter->left << " <--> "<< iter->right <<std::endl;
    }
}





/*
 * Creating index
 */
void thread_test::create_index::reference_index_hash(uint64_t &sequence_length, int &split,
        std::string &sequence_content, int i  ){

    uint64_t seq_strt = 0;

//  set seq_strt
    if(i == 0)
        seq_strt = sequence_length * i;
    else
        seq_strt = sequence_length * i + 1;

    for (uint64_t seq_itr = seq_strt; seq_itr <= sequence_length; ++seq_itr ){


        std::string splitstr = sequence_content.substr(seq_itr, split);     

        mtx.lock();
        //std::lock_guard<std::mutex> lock(mtx);
        reference_index_vector.insert(position(seq_itr, splitstr));
        mtx.unlock();

        seq_itr += split-1;     

    }
}

parallel_index.h

#ifndef PARALLEL_INDEX_H_
#define PARALLEL_INDEX_H_


#include<iostream>
#include <algorithm>
#include <utility>
#include <boost/bimap.hpp>
#include <boost/bimap/unordered_set_of.hpp>
#include <boost/bimap/unordered_multiset_of.hpp>

namespace bimaps = boost::bimaps;

typedef boost::bimap<bimaps::unordered_set_of<uint64_t>,
        bimaps::unordered_multiset_of<std::string > > bimap_reference;
typedef bimap_reference::value_type position;
extern bimap_reference reference_index_vector;


namespace thread_test{

class create_index{
public:
    void reference_index_hash(uint64_t &sequence_length, int &split,
            std::string &sequence_content, int i);
};
}


#endif /* PARALLEL_INDEX_H_ */

Answer 1

我觉得 segmentation fault 的罪魁祸首不过是库的 static 链接。它不是通过将 seq_itr 递增到大于实际序列长度的值，因为如果 seq_itr 大于实际序列长度，您的 for 循环将永远不允许进入。您尝试删除 -static 标志，它应该可以通过不给出段错误来工作，但是它不能保证其他代码的正确性。有关 thread 的段错误的更多详细信息，请参见 here