C程序演示产生僵死进程的过程

Posted 2020-09-18 gavanwanggw

先抄录网上一段对僵死进程的描写叙述：

僵尸进程：一个进程使用fork创建子进程，假设子进程退出，而父进程并没有调用wait或waitpid获取子进程的状态信息，那么子进程的进程描写叙述符仍然保存在系统中。

这样的进程称之为僵死进程。在每一个进程退出的时候,内核释放该进程全部的资源,包含打开的文件,占用的内存等。 可是仍然为其保留一定的信息(包含进程号the process ID,退出状态the termination status of the process,执行时间the amount of CPU time taken by the process等)。直到父进程通过wait / waitpid来取时才释放。

但这样就导致了问题。假设进程不调用wait / waitpid的话。 那么保留的那段信息就不会释放，其进程号就会一直被占用，可是系统所能使用的进程号是有限的，假设大量的产生僵死进程，将由于没有可用的进程号而导致系统不能产生新的进程. 此即为僵尸进程的危害，应当避免。

从系统角度来说。处理僵尸进程有两种方法：

1 找到僵死进程的父进程，kill掉父进程。那么僵死进程将变为孤儿进程。孤儿进程在系统中由init进程接管。init进程将回收僵死进程的资源
2 reboot系统，由于僵死进程是不能够被kill掉

例如以下測试：

[[email protected] ~]# ps -ef|grep 21165
root     21165  7459  0 05:51 pts/1    00:00:00 ./a.out
root     21166 21165  0 05:51 pts/1    00:00:00 [a.out] <defunct>
root     21190  8866  0 05:52 pts/3    00:00:00 grep 21165
[[email protected] ~]# kill 21165
[[email protected] ~]# 
[[email protected] ~]# 
[[email protected] ~]# ps -ef|grep 21165  杀掉父进程后。子进程也消失
root     21196  8866  0 05:52 pts/3    00:00:00 grep 21165

[[email protected] ~]# ps -ef|grep 16704
root     16704 16703  0 04:06 pts/1    00:00:00 [a.out] <defunct>
root     16719  8866  0 04:06 pts/3    00:00:00 grep 16704
[[email protected] ~]# 
[[email protected] ~]# 
[[email protected] ~]# kill -9 16704
[[email protected] ~]# 
[[email protected] ~]# ps -ef|grep 16704
root     16704 16703  0 04:06 pts/1    00:00:00 [a.out] <defunct>
root     16725  8866  0 04:06 pts/3    00:00:00 grep 16704

</pre><p></p><p>从开发角度。有两种方法来避免僵死进程：1 通过signal函数处理。由于每个子进程退出都会向父进程发生一个SIGCHILD信号2 通过fork两次子进程实现，使子进程的父进程为init进程（），大多数守护进程就是这样实现的简单程序演示产生僵死进程的过程：</p><pre code_snippet_id="554626" snippet_file_name="blog_20141217_3_6668512" name="code" class="cpp">一 父进程fork一个子进程然后不使用waitpid函数，直接退出，而子进程sleep 120秒后退出

#include <sys/types.h>
#include <sys/wait.h>
#include <errno.h>
#include <unistd.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>


int main(int argc, char *argv[])
{
        pid_t pid;

        pid = fork();
        if (pid == 0) {

                int iPid = (int)getpid();
                fprintf(stderr,"I am child,%d\n",iPid);
                sleep(120);
                fprintf(stderr, "Child exits\n");

                return EXIT_SUCCESS;
        }
       int iPid = (int)getpid();
       fprintf(stderr,"I am parent,%d\n",iPid);
       fprintf(stderr, "parent exits\n");
       return EXIT_SUCCESS;
}


[[email protected] ~]# gcc Zom.c 
[[email protected] ~]# ./a.out 

[[email protected] ~]# ./a.out 
I am parent,15019
parent exits
I am child,15020

从输出看父进程先退出。然后子进程执行sleep函数


[[email protected] ~]# ps -ef|grep 15019 //查看父进程
root     15046  8866  0 03:29 pts/3    00:00:00 grep 15019
[[email protected] ~]# 
[[email protected] ~]# ps -ef|grep 15020 //查看子进程
root     15020     1  0 03:29 pts/1    00:00:00 ./a.out
root     15056  8866  0 03:29 pts/3    00:00:00 grep 15020
	
从ps看父进程已经销毁，子进程的父进程号为1，也就是init进程
	

二 父进程fork一个子进程然后使用waitpid函数，然后退出，而子进程sleep 120秒后退出

#include <sys/types.h>
#include <sys/wait.h>
#include <errno.h>
#include <unistd.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>


int main(int argc, char *argv[])
{
        pid_t pid;

        pid = fork();
        if (pid == 0) {

                int iPid = (int)getpid();
                fprintf(stderr,"I am child,%d\n",iPid);
                sleep(120);
                fprintf(stderr, "Child exits\n");

                return EXIT_SUCCESS;
        }
       int iPid = (int)getpid();
       fprintf(stderr,"I am parent,%d\n",iPid);
       waitpid(pid,NULL,0);
       fprintf(stderr, "parent exits\n");
       return EXIT_SUCCESS;
}

[[email protected] ~]# gcc Zom.c 
[[email protected] ~]# ./a.out 
I am parent,15187
I am child,15188
Child exits
parent exits

从输出看子进程先退出，父进程一直等待子进程退出后才退出


[[email protected] ~]# ps -ef|grep 15187  //查看父进程
root     15187  7459  0 03:32 pts/1    00:00:00 ./a.out
root     15188 15187  0 03:32 pts/1    00:00:00 ./a.out
root     15197  8866  0 03:33 pts/3    00:00:00 grep 15187
[[email protected] ~]# ps -ef|grep 15188  //查看子进程
root     15188 15187  0 03:32 pts/1    00:00:00 ./a.out
root     15207  8866  0 03:33 pts/3    00:00:00 grep 15188
	
	

三 父进程fork一个子进程。然后使用waitpid函数，最后使用sleep函数，而子进程sleep 40秒后退出
#include <sys/types.h>
#include <sys/wait.h>
#include <errno.h>
#include <unistd.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>


int main(int argc, char *argv[])
{
        pid_t pid;

        pid = fork();
        if (pid == 0) {

                int iPid = (int)getpid();
                fprintf(stderr,"I am child,%d\n",iPid);
                sleep(40);
                fprintf(stderr, "Child exits\n");

                return EXIT_SUCCESS;
        }
       int iPid = (int)getpid();
       fprintf(stderr,"I am parent,%d\n",iPid);
       waitpid(pid,NULL,0);
       fprintf(stderr, "sleep....\n");
       sleep(120);
       fprintf(stderr, "parent exits\n");
       return EXIT_SUCCESS;
}


[[email protected] ~]# ./a.out 
I am parent,15673
I am child,15674
Child exits  //等待40秒后输出
sleep....  //等待40秒后输出
parent exits

从上面的输出看sleep函数没有立马执行，而是等待子进程执行完毕才执行，实际是在等待waitpid函数返回


[[email protected] ~]# ps -ef|grep 15673  //程序执行40秒内
root     15673  7459  0 03:43 pts/1    00:00:00 ./a.out
root     15674 15673  0 03:43 pts/1    00:00:00 ./a.out
root     15681  8866  0 03:44 pts/3    00:00:00 grep 15673
[[email protected] ~]# ps -ef|grep 15674 //程序执行40秒内
root     15674 15673  0 03:43 pts/1    00:00:00 ./a.out
root     15692  8866  0 03:44 pts/3    00:00:00 grep 15674
[[email protected] ~]# 
[[email protected] ~]# ps -ef|grep 15673   //程序执行40秒外
root     15673  7459  0 03:43 pts/1    00:00:00 ./a.out
root     15725  8866  0 03:44 pts/3    00:00:00 grep 15673
[[email protected] ~]# ps -ef|grep 15674  //程序执行40秒外，子进程已经销毁
root     15727  8866  0 03:44 pts/3    00:00:00 grep 15674
[[email protected] ~]# 
[[email protected] ~]# ps -ef|grep 15673  //程序执行120秒外
root     15798  8866  0 03:46 pts/3    00:00:00 grep 15673
	
	

四 父进程fork一个子进程。不使用waitpid函数然，而是sleep 120秒，而子进程sleep 1秒后退出
	
#include <sys/types.h>
#include <sys/wait.h>
#include <errno.h>
#include <unistd.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>


int main(int argc, char *argv[])
{
        pid_t pid;

        pid = fork();
        if (pid == 0) {

                int iPid = (int)getpid();
                fprintf(stderr,"I am child,%d\n",iPid);
                sleep(1);
                fprintf(stderr, "Child exits\n");

                return EXIT_SUCCESS;
        }
       int iPid = (int)getpid();
       fprintf(stderr,"I am parent,%d\n",iPid);
       fprintf(stderr, "sleep....\n");
       sleep(120);
       fprintf(stderr, "parent exits\n");
       return EXIT_SUCCESS;
}

[[email protected] ~]# ./a.out 
I am parent,16026
sleep....
I am child,16027
Child exits
parent exits

从上面输出看子进程先于父进程退出


[[email protected] ~]# ps -ef|grep 16026  //查看父进程
root     16026  7459  0 03:51 pts/1    00:00:00 ./a.out
root     16027 16026  0 03:51 pts/1    00:00:00 [a.out] <defunct>
root     16039  8866  0 03:51 pts/3    00:00:00 grep 16026 
[[email protected] ~]# 
[[email protected] ~]# ps -ef|grep 16027   //查看子进程，子进程处于僵死状态
root     16027 16026  0 03:51 pts/1    00:00:00 [a.out] <defunct>
root     16046  8866  0 03:51 pts/3    00:00:00 grep 16027

[[email protected] ~]# top   //top 进程显示存在一个僵死进程

top - 04:02:20 up  2:46,  4 users,  load average: 0.21, 0.15, 0.15
Tasks: 280 total,   1 running, 278 sleeping,   0 stopped,   1 zombie
Cpu(s):  1.2%us,  0.6%sy,  0.0%ni, 97.4%id,  0.7%wa,  0.0%hi,  0.0%si,  0.0%st
Mem:   2050752k total,  1819480k used,   231272k free,   141876k buffers
Swap:  6291448k total,        0k used,  6291448k free,   775368k cached
	
	
[[email protected] ~]# ps -ef|grep 16027    //120秒后僵死进程消失
root     16513  8866  0 04:01 pts/3    00:00:00 grep 16027