Question

I use boost trim function and find it perform very well in single-thread environment.

But when I call trim function in multi-thread environment, it will have a poor performance.
I also find that it will have a good performance when call it using multi-process method.

In the end, I write a simple trim function, it perform very well in multi-thread environment or multi-process environment.

I think I must use it incorrectly in multi-thread environment.
So I want to know what’s wrong.

Thanks for any reply.

boost version: boost 1.46.1
os: linux redhat 6.1, 8core, 24G memory.

the blow is sample code
test1.cpp, call trim function in multi-thread environment

//----------------------------
---------------------
using namespace std;
using namespace boost;

void *TrimNString(void *arg) {

    string base ="fdsffdsafdsa";
    for(int i = 0; i != 50000000;i++)
    {
        string str = base;
        trim(str);
    }
    return 0;
}

int main()
{

    //8 threads to call trim function
    system("date");
    pthread_t mythread1, mythread2, mythread3, mythread4, mythread5, mythread6, mythread7,mythread8;
    pthread_create(&mythread1, NULL, TrimNString, NULL);
    pthread_create(&mythread2, NULL, TrimNString, NULL);
    pthread_create(&mythread3, NULL, TrimNString, NULL);
    pthread_create(&mythread4, NULL, TrimNString, NULL);
    pthread_create(&mythread5, NULL, TrimNString, NULL);
    pthread_create(&mythread6, NULL, TrimNString, NULL);
    pthread_create(&mythread7, NULL, TrimNString, NULL);
    pthread_create(&mythread8, NULL, TrimNString, NULL);

    pthread_join(mythread1, NULL);
    pthread_join(mythread2, NULL);
    pthread_join(mythread3, NULL);
    pthread_join(mythread4, NULL);
    pthread_join(mythread5, NULL);
    pthread_join(mythread6, NULL);
    pthread_join(mythread7, NULL);
    pthread_join(mythread8, NULL);
    system("date");
    return 0;
}

test2.cpp, call trim function in multi-process environment

//-------------------------------------------------
/*
 * test.cpp
 *
 *  Created on: 2012-6-19
 *      Author: root
 */



#include<pthread.h>
#include <boost/algorithm/string.hpp>
#include <string>
#include <vector>
#include <cstdlib>
#include <iostream>
using namespace std;
using namespace boost;


void *TrimNString(void *arg) {

    system("./TrimNString");// TrimNString is produced by test3.cpp


    return 0;
}

int main()
{

    //8 process to call trim function
    system("date");
    pthread_t mythread1, mythread2, mythread3, mythread4, mythread5, mythread6, mythread7,mythread8;
    pthread_create(&mythread1, NULL, TrimNString, NULL);
    pthread_create(&mythread2, NULL, TrimNString, NULL);
    pthread_create(&mythread3, NULL, TrimNString, NULL);
    pthread_create(&mythread4, NULL, TrimNString, NULL);
    pthread_create(&mythread5, NULL, TrimNString, NULL);
    pthread_create(&mythread6, NULL, TrimNString, NULL);
    pthread_create(&mythread7, NULL, TrimNString, NULL);
    pthread_create(&mythread8, NULL, TrimNString, NULL);

    pthread_join(mythread1, NULL);
    pthread_join(mythread2, NULL);
    pthread_join(mythread3, NULL);
    pthread_join(mythread4, NULL);
    pthread_join(mythread5, NULL);
    pthread_join(mythread6, NULL);
    pthread_join(mythread7, NULL);
    pthread_join(mythread8, NULL);
    system("date");
    return 0;
}

test3.cpp, the executable file for test2.cpp

/*
 * test.cpp
 *
 *  Created on: 2012-6-19
 *      Author: root
 */



#include<pthread.h>
#include <boost/algorithm/string.hpp>
#include <string>
#include <vector>
#include <cstdlib>
#include <iostream>
using namespace std;
using namespace boost;


//produce the executable file
int main()
{
    string base ="fdsffdsafdsa";
    for(int i = 0; i != 50000000;i++)
    {
        string str = base;
        trim(str);
    }
    return 0;
}

test4.cpp, call a simple trim(not boost library) function in multi-thread environment, it has similary performance like multi-process calling.

//-------------------------------------------------
#include<pthread.h>
#include <boost/algorithm/string.hpp>
#include <string>
#include <vector>
#include <cstdlib>
#include <iostream>
using namespace std;
using namespace boost;

void ltrim(string & str)
{
    if(str.find_first_not_of(" \n\r\t") != string::npos)
    {
        str = str.substr(str.find_first_not_of(" \n\r\t"));
    }

}

void rtrim(string & str)
{
    if(str.find_first_not_of(" \n\r\t") != string::npos)
    {
        str = str.substr(0, str.find_last_not_of(" \n\r\t") + 1);
    }

}

void trimStr(string &str)
{
    ltrim(str);
    rtrim(str);
}

void *TrimNString(void *arg) {

    string base ="fdsffdsafdsa";
    for(int i = 0; i != 50000000;i++)
    {
        string str = base;
        trimStr(str);
    }
    return 0;
}

int main()
{

    //8 threads to call trim function
    system("date");
    pthread_t mythread1, mythread2, mythread3, mythread4, mythread5, mythread6, mythread7,mythread8;
    pthread_create(&mythread1, NULL, TrimNString, NULL);
    pthread_create(&mythread2, NULL, TrimNString, NULL);
    pthread_create(&mythread3, NULL, TrimNString, NULL);
    pthread_create(&mythread4, NULL, TrimNString, NULL);
    pthread_create(&mythread5, NULL, TrimNString, NULL);
    pthread_create(&mythread6, NULL, TrimNString, NULL);
    pthread_create(&mythread7, NULL, TrimNString, NULL);
    pthread_create(&mythread8, NULL, TrimNString, NULL);

    pthread_join(mythread1, NULL);
    pthread_join(mythread2, NULL);
    pthread_join(mythread3, NULL);
    pthread_join(mythread4, NULL);
    pthread_join(mythread5, NULL);
    pthread_join(mythread6, NULL);
    pthread_join(mythread7, NULL);
    pthread_join(mythread8, NULL);
    system("date");
    return 0;
}

Answer 1

You are not supplying a locale so trim will use the current locale. Fetching the current locale probably need a lock which might cause your performance problem.

try to create the locale once and use it in all trim calls

std::locale mylocale = std::locale();

...

trim(str, mylocale);