我必须阻止主线程上的信号来处理另一个线程上的取消点吗？

Question

当我在一个运行在专用线程中的TCP服务器上工作时，我注意到信号处理中的奇怪行为。我已经准备了以下MWE（我使用cerr来避免调试打印时的争用情况）：

#include <signal.h>
#include <unistd.h>

#include <iostream>
#include <thread>
#include <chrono>

using namespace std;

#undef THREAD

class RaiiObject
{
public:
    RaiiObject() { cerr << "RaiiObject ctor" << endl; }
    ~RaiiObject() { cerr << "RaiiObject dtor" << endl; }
};

static void signalHandler(int sig)
{
    write(2, "Signal\n", 7);
}

static void blockSigint()
{
    sigset_t blockset;

    sigemptyset(&blockset);
    sigaddset(&blockset, SIGINT);
    sigprocmask(SIG_BLOCK, &blockset, NULL);
}

static void setSigintHandler()
{
    struct sigaction sa;
    sa.sa_handler = signalHandler;
    sa.sa_flags = 0;
    sigemptyset(&sa.sa_mask);
    sigaction(SIGINT, &sa, NULL);
}

void runSelect()
{
    sigset_t emptyset;
    sigemptyset(&emptyset);

    setSigintHandler();

    RaiiObject RaiiObject{};
    fd_set fdRead;

    while (true) {
        cerr << "Loop iteration" << endl;
        FD_ZERO(&fdRead);
        FD_SET(0, &fdRead);
        while (true) {
            if (pselect(FD_SETSIZE, &fdRead, NULL, NULL, NULL, &emptyset) > 0) {
                cerr << "Select" << endl;
            } else {
                cerr << "Select break" << endl;
                return;
            }
        }
    }
}

int main()
{
    cerr << "Main start" << endl;

#ifdef THREAD
    cerr << "Thread start" << endl;
    //blockSigint();
    thread{runSelect}.join();
#else
    runSelect();
#endif

    cerr << "Main exit" << endl;

    return EXIT_SUCCESS;
}

当我编译一个单线程程序(#undef thread)时，我可以用Ctrl-C正确地终止runSelect（）函数：

Main start
RaiiObject ctor
Loop iteration
^CSignal
Select break
RaiiObject dtor
Main exit

但是当我编译一个多线程(#define thread)程序时，它挂在信号处理程序上：

Main start
RaiiObject ctor
Loop iteration
^CSignal

14:46:53.543360 write(2, "Loop iteration", 14Loop iteration) = 14
14:46:53.543482 write(2, "\n", 1
)       = 1
14:46:53.543586 pselect6(1024, [0], NULL, NULL, NULL, {[], 8}) = ? ERESTARTNOHAND (To be restarted if no handler)
14:46:55.286989 --- SIGINT {si_signo=SIGINT, si_code=SI_USER, si_pid=2707461, si_uid=1000} ---
14:46:55.287120 write(2, "Signal\n", 7Signal
) = 7
14:46:55.287327 rt_sigreturn({mask=[]}) = -1 EINTR (Interrupted system call)
14:46:55.287569 write(2, "Select break", 12Select break) = 12
14:46:55.287760 write(2, "\n", 1

[pid 3469011] 14:48:37.211792 write(2, "Loop iteration", 14Loop iteration) = 14
[pid 3469011] 14:48:37.211916 write(2, "\n", 1
) = 1
[pid 3469011] 14:48:37.212031 pselect6(1024, [0], NULL, NULL, NULL, {[], 8} <unfinished ...>
[pid 3469010] 14:48:40.046146 <... futex resumed>) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 3469010] 14:48:40.046256 --- SIGINT {si_signo=SIGINT, si_code=SI_USER, si_pid=2707461, si_uid=1000} ---
[pid 3469010] 14:48:40.046354 write(2, "Signal\n", 7Signal
) = 7
[pid 3469010] 14:48:40.046588 rt_sigreturn({mask=[]}) = -1 EINTR (Interrupted system call)
[pid 3469010] 14:48:40.046821 futex(0x7f4e5c16b9d0, FUTEX_WAIT, 3469011, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)

Answer 1

我必须阻止主线程上的信号来处理另一个线程上的取消点吗？

您需要只允许（解除屏蔽）那些希望处理信号的线程中的信号，并在其他线程中阻止它们。

操作系统将向任何可以接收的线程发送一个进程导向的信号。终端的SIGINT被发送到前台进程组中的每个进程，操作系统决定每个进程的哪个线程将接收它。

time  thr1        thr2
----  ----------  ------
  0   block(INT)   - 
  1   run thread  (awake)    <---- SIGINT
  3   join()      pselect()
  4   ...         ...