几种线程本地存储变量和普通变量的性能比较

本文来源于libGod官网http://www.libgod.com，转载请注明来源

God一直致力于研究高并发服务端的开发，这次要优化的是libGod库中的线程本地存储变量，线程本地存储变量访问非常频繁，优化后库的性能应该会提高不少。已知的线程本地存储方法有boost中的thread_specific_ptr类，gcc中的__thread关键字，pthread中的pthread_getspecific函数。这次测试这3中本地存储以及普通变量之间的性能差别，代码如下：

#include <iostream>
#include <stdio.h>
#include <pthread.h>
#include <boost/thread/thread.hpp>
#include <boost/thread/tss.hpp>

using namespace std;

class C {
public:
    C(int a) {
        m_a = a;
        printf("C() %d\n", m_a);
    }
    ~C() {
        printf("~C() %d\n", m_a);
    }

private:
    int m_a;
};

#define TM 3

#if TM == 1
    boost::thread_specific_ptr<C> pc;
    const char *testType = "boost";
#elif TM == 2
    __thread C *pc;
    const char *testType = "__thread";
#elif TM == 3
    pthread_key_t pc;
    const char *testType = "pthread";
#else
    C *pc;
    const char *testType = "normal";
#endif

void boostthreadFunc() {
#if TM == 1
    pc.reset(new C(10));
#elif TM == 2
    pc = new C(20);
#elif TM == 3
    if (pthread_key_create(&pc, NULL)) {
        cout << "pthread_key_create" << endl;
        return;
    }
    if (pthread_setspecific(pc, new C(30))) {
        cout << "pthread_setspecific" << endl;
        return;
    }
#else
    pc = new C(20);
#endif
    int switches = 5000000;
    int i = switches;
    struct timeval tm_start, tm_end;
    gettimeofday(&tm_start, NULL);
    while (i--) {
#if TM == 1
        C *c1 = pc.get();
        C *c2 = pc.get();
        C *c3 = pc.get();
        C *c4 = pc.get();
        C *c5 = pc.get();

        C *c6 = pc.get();
        C *c7 = pc.get();
        C *c8 = pc.get();
        C *c9 = pc.get();
        C *c10 = pc.get();

        C *c11 = pc.get();
        C *c12 = pc.get();
        C *c13 = pc.get();
        C *c14 = pc.get();
        C *c15 = pc.get();

        C *c16 = pc.get();
        C *c17 = pc.get();
        C *c18 = pc.get();
        C *c19 = pc.get();
        C *c20 = pc.get();

        C *c21 = pc.get();
        C *c22 = pc.get();
        C *c23 = pc.get();
        C *c24 = pc.get();
        C *c25 = pc.get();

        C *c26 = pc.get();
        C *c27 = pc.get();
        C *c28 = pc.get();
        C *c29 = pc.get();
        C *c30 = pc.get();

        C *c31 = pc.get();
        C *c32 = pc.get();
        C *c33 = pc.get();
        C *c34 = pc.get();
        C *c35 = pc.get();

        C *c36 = pc.get();
        C *c37 = pc.get();
        C *c38 = pc.get();
        C *c39 = pc.get();
        C *c40 = pc.get();

#elif TM == 2
        C *c1 = pc;
        C *c2 = pc;
        C *c3 = pc;
        C *c4 = pc;
        C *c5 = pc;

        C *c6 = pc;
        C *c7 = pc;
        C *c8 = pc;
        C *c9 = pc;
        C *c10 = pc;

        C *c11 = pc;
        C *c12 = pc;
        C *c13 = pc;
        C *c14 = pc;
        C *c15 = pc;

        C *c16 = pc;
        C *c17 = pc;
        C *c18 = pc;
        C *c19 = pc;
        C *c20 = pc;

        C *c21 = pc;
        C *c22 = pc;
        C *c23 = pc;
        C *c24 = pc;
        C *c25 = pc;

        C *c26 = pc;
        C *c27 = pc;
        C *c28 = pc;
        C *c29 = pc;
        C *c30 = pc;

        C *c31 = pc;
        C *c32 = pc;
        C *c33 = pc;
        C *c34 = pc;
        C *c35 = pc;

        C *c36 = pc;
        C *c37 = pc;
        C *c38 = pc;
        C *c39 = pc;
        C *c40 = pc;

#elif TM == 3
        C *c1 = (C *)pthread_getspecific(pc);
        C *c2 = (C *)pthread_getspecific(pc);
        C *c3 = (C *)pthread_getspecific(pc);
        C *c4 = (C *)pthread_getspecific(pc);
        C *c5 = (C *)pthread_getspecific(pc);

        C *c6 = (C *)pthread_getspecific(pc);
        C *c7 = (C *)pthread_getspecific(pc);
        C *c8 = (C *)pthread_getspecific(pc);
        C *c9 = (C *)pthread_getspecific(pc);
        C *c10 = (C *)pthread_getspecific(pc);

        C *c11 = (C *)pthread_getspecific(pc);
        C *c12 = (C *)pthread_getspecific(pc);
        C *c13 = (C *)pthread_getspecific(pc);
        C *c14 = (C *)pthread_getspecific(pc);
        C *c15 = (C *)pthread_getspecific(pc);

        C *c16 = (C *)pthread_getspecific(pc);
        C *c17 = (C *)pthread_getspecific(pc);
        C *c18 = (C *)pthread_getspecific(pc);
        C *c19 = (C *)pthread_getspecific(pc);
        C *c20 = (C *)pthread_getspecific(pc);

        C *c21 = (C *)pthread_getspecific(pc);
        C *c22 = (C *)pthread_getspecific(pc);
        C *c23 = (C *)pthread_getspecific(pc);
        C *c24 = (C *)pthread_getspecific(pc);
        C *c25 = (C *)pthread_getspecific(pc);

        C *c26 = (C *)pthread_getspecific(pc);
        C *c27 = (C *)pthread_getspecific(pc);
        C *c28 = (C *)pthread_getspecific(pc);
        C *c29 = (C *)pthread_getspecific(pc);
        C *c30 = (C *)pthread_getspecific(pc);

        C *c31 = (C *)pthread_getspecific(pc);
        C *c32 = (C *)pthread_getspecific(pc);
        C *c33 = (C *)pthread_getspecific(pc);
        C *c34 = (C *)pthread_getspecific(pc);
        C *c35 = (C *)pthread_getspecific(pc);

        C *c36 = (C *)pthread_getspecific(pc);
        C *c37 = (C *)pthread_getspecific(pc);
        C *c38 = (C *)pthread_getspecific(pc);
        C *c39 = (C *)pthread_getspecific(pc);
        C *c40 = (C *)pthread_getspecific(pc);

#else
        C *c1 = pc;
        C *c2 = pc;
        C *c3 = pc;
        C *c4 = pc;
        C *c5 = pc;

        C *c6 = pc;
        C *c7 = pc;
        C *c8 = pc;
        C *c9 = pc;
        C *c10 = pc;

        C *c11 = pc;
        C *c12 = pc;
        C *c13 = pc;
        C *c14 = pc;
        C *c15 = pc;

        C *c16 = pc;
        C *c17 = pc;
        C *c18 = pc;
        C *c19 = pc;
        C *c20 = pc;

        C *c21 = pc;
        C *c22 = pc;
        C *c23 = pc;
        C *c24 = pc;
        C *c25 = pc;

        C *c26 = pc;
        C *c27 = pc;
        C *c28 = pc;
        C *c29 = pc;
        C *c30 = pc;

        C *c31 = pc;
        C *c32 = pc;
        C *c33 = pc;
        C *c34 = pc;
        C *c35 = pc;

        C *c36 = pc;
        C *c37 = pc;
        C *c38 = pc;
        C *c39 = pc;
        C *c40 = pc;

#endif
    }
    gettimeofday(&tm_end, NULL);
    switches *= 40;
    long long ns = (tm_end.tv_sec - tm_start.tv_sec) * 1000LL * 1000LL * 1000LL +
        (tm_end.tv_usec - tm_start.tv_usec) * 1000LL;
    std::cout << "####Benchmark result#### " << testType << std::endl;
    std::cout << "Totol switches : " << switches << std::endl;
    std::cout << "Cost per switch(ns) : " << (double)ns/switches << std::endl;
    std::cout << "All cost switch(ns) : " << ns << std::endl;
    std::cout << "####Benchmark result####" << std::endl;
}

int main() {
    boost::thread bt(&boostthreadFunc);
    bt.join();
    printf("main exit..\n");
    return 0;
}

 详情请访问libgod官网..