在启动时停止子进程

Question

我正在尝试实现一个检查点函数来检查进程。我通过分叉子进程来做到这一点。但是我需要在开始时暂停子进程。稍后，我们可以通过取消暂停子进程并使父进程自行终止来从检查点重新启动。

以下是我为 checkpoint 和 restart_from_checkpoint 编写的代码以及如何调用它们的示例。

#include <stdio.h>
#include <unistd.h>
#include <sys/ptrace.h>
#include <sys/wait.h>

pid_t checkpoint();
void restart_from_checkpoint( pid_t pid );

int main( int argc, char *argv[] )
{
  int i;
  pid_t child_pid;
  pid_t parent_pid = getpid();

  for( i = 0; i < 10; i++ )
  {
    if ( i == 4 )
    {
      printf( "%6s: Checkpointing!\n", (getpid() == parent_pid)? "parent":"child" );
      child_pid = checkpoint();
    }

    if ( i == 7 )
    {
      printf( "%6s: Restarting!\n", (getpid() == parent_pid)? "parent":"child" );
      restart_from_checkpoint( child_pid );
    }

    printf( "%6s: i = %d\n", (getpid() == parent_pid)? "parent":"child", i );
  }

  return 0;
}

pid_t checkpoint()
{
    pid_t pid;
    int wait_val;

    switch (pid=fork()) 
    {
    case -1: 
        perror("fork"); 
        break;
    case 0:         // child process starts
        ptrace(PTRACE_TRACEME,0,0,0);
        raise( SIGTRAP ); // Note that this is the solution to first part
                              // of the question, which I added after
                              // asking this question.
        break;  // child process ends
    default:        // parent process starts
        wait(&wait_val);
        return pid;
    }
}

void restart_from_checkpoint( pid_t pid )
{
    ptrace(PTRACE_CONT, pid, NULL, NULL);
    wait(NULL); // I'm just waiting here, but actually 
                //  I need to kill the calling process.
}

我不知道如何在调用 ptrace(PTRACE_TRACEME,0,0,0) 后停止子进程。其次，我不知道如何终止父进程，同时让子进程在 restart_from_checkpoint 处继续。

最好的办法是可以在 ptrace 中使用一个参数，该参数可以在开始时停止分叉进程，并在稍后使用 PTRACE_CONT 启动。不幸的是，PTRACE_TRACEME 仅在 exec 函数调用处停止。

Answer 1

您可以使用 IPC 信号量或 SIGNAL USR1...

Answer 2

好的，我找到了解决方案。它现在工作得很好。这是感兴趣的人的代码。

#include <stdio.h>
#include <unistd.h>
#include <sys/ptrace.h>
#include <sys/wait.h>
#include <stdlib.h>

pid_t checkpoint();
void restart_from_checkpoint( pid_t pid );

int main( int argc, char *argv[] )
{
  int i;
  pid_t child_pid;
  pid_t parent_pid = getpid();

  for( i = 0; i < 10; i++ )
  {
    if ( i == 4 )
    {
      printf( "%6s: Checkpointing!\n", (getpid() == parent_pid)? "parent":"child" );
      child_pid = checkpoint();
    }

    if ( i == 7 && ( getpid() == parent_pid ) )
    {
      printf( "%6s: Restarting!\n", (getpid() == parent_pid)? "parent":"child" );
      restart_from_checkpoint( child_pid );
    }

    printf( "%6s: i = %d\n", (getpid() == parent_pid)? "parent":"child", i );
  }

  return 0;
}

pid_t checkpoint()
{
    pid_t pid;
    int wait_val;

    switch (pid=fork()) 
    {
    case -1: 
        perror("fork"); 
        break;
    case 0:         // child process starts
        ptrace(PTRACE_TRACEME,0,0,0);
        raise(SIGTRAP);
        break;  // child process ends
    default:        // parent process starts
        wait(&wait_val);
        return pid;
    }
}

void restart_from_checkpoint( pid_t pid )
{
    ptrace(PTRACE_CONT, pid, NULL, NULL);
    ptrace(PTRACE_DETACH, pid, NULL, NULL);
    exit( 1 );
}