kill bgwriter 的小实验

如果 我直接 kill 掉 bgwriter 的进程，会发生什么呢？

[root@localhost postgresql-9.2.0]# ps -ef|grep post

root      2928  2897  0 10:34 pts/1    00:00:00 su - postgres

postgres  2929  2928  0 10:34 pts/1    00:00:00 -bash

postgres  3101  2929  0 11:09 pts/1    00:00:00 ./postgres -D /usr/local/pgsql/data

postgres  3103  3101  0 11:09 ?        00:00:00 postgres: checkpointer process     

postgres  3104  3101  0 11:09 ?        00:00:00 postgres: writer process           

postgres  3105  3101  0 11:09 ?        00:00:00 postgres: wal writer process       

postgres  3106  3101  0 11:09 ?        00:00:00 postgres: autovacuum launcher process   

postgres  3107  3101  0 11:09 ?        00:00:00 postgres: stats collector process   

root      3109  2977  0 11:10 pts/2    00:00:00 grep post

[root@localhost postgresql-9.2.0]# kill 3104

[root@localhost postgresql-9.2.0]# ps -ef|grep post

root      2928  2897  0 10:34 pts/1    00:00:00 su - postgres

postgres  2929  2928  0 10:34 pts/1    00:00:00 -bash

postgres  3101  2929  0 11:09 pts/1    00:00:00 ./postgres -D /usr/local/pgsql/data

postgres  3103  3101  0 11:09 ?        00:00:00 postgres: checkpointer process     

postgres  3105  3101  0 11:09 ?        00:00:00 postgres: wal writer process       

postgres  3106  3101  0 11:09 ?        00:00:00 postgres: autovacuum launcher process   

postgres  3107  3101  0 11:09 ?        00:00:00 postgres: stats collector process   

postgres  3110  3101  0 11:10 ?        00:00:00 postgres: writer process           

root      3112  2977  0 11:10 pts/2    00:00:00 grep post

[root@localhost postgresql-9.2.0]# kill 3110

[root@localhost postgresql-9.2.0]# ps -ef|grep post

root      2928  2897  0 10:34 pts/1    00:00:00 su - postgres

postgres  2929  2928  0 10:34 pts/1    00:00:00 -bash

postgres  3101  2929  0 11:09 pts/1    00:00:00 ./postgres -D /usr/local/pgsql/data

postgres  3103  3101  0 11:09 ?        00:00:00 postgres: checkpointer process     

postgres  3105  3101  0 11:09 ?        00:00:00 postgres: wal writer process       

postgres  3106  3101  0 11:09 ?        00:00:00 postgres: autovacuum launcher process   

postgres  3107  3101  0 11:09 ?        00:00:00 postgres: stats collector process   

postgres  3114  3101  0 11:10 ?        00:00:00 postgres: writer process           

root      3116  2977  0 11:10 pts/2    00:00:00 grep post

[root@localhost postgresql-9.2.0]# 

我删除了几次 bgwriter 的进程，都再次生成了。

那么其原因是什么呢？

这和 postmaster.c 的监控有关。来看代码吧：为简化起见，吧postmaster 与 postgres 当成一个东西。

postmaster 生成了各个子进程以后，会在一旁进行监控:

/*                                    

 * Reaper -- signal handler to cleanup after a child process dies.                                    

 */                                    

static void                                    

reaper(SIGNAL_ARGS)                                    

{                                    

    int            save_errno = errno;                    

    int            pid;        /* process id of dead child process */            

    int            exitstatus;        /* its exit status */            

                                    

    /* These macros hide platform variations in getting child status */                                

#ifdef HAVE_WAITPID                                    

    int            status;            /* child exit status */        

                                    

#define LOOPTEST()            ((pid = waitpid(-1, &status, WNOHANG)) > 0)                        

#define LOOPHEADER()            (exitstatus = status)                        

#else                            /* !HAVE_WAITPID */        

#ifndef WIN32                                    

    union wait    status;            /* child exit status */                

                                    

#define LOOPTEST()        ((pid = wait3(&status, WNOHANG, NULL)) > 0)                            

#define LOOPHEADER()    (exitstatus = status.w_status)                                

#else                            /* WIN32 */        

#define LOOPTEST()        ((pid = win32_waitpid(&exitstatus)) > 0)                            

#define LOOPHEADER()                                    

#endif   /* WIN32 */                                    

#endif   /* HAVE_WAITPID */                                    

                                    

    PG_SETMASK(&BlockSig);                                

                                    

    ereport(DEBUG4,                                

            (errmsg_internal("reaping dead processes")));                        

                                    

    while (LOOPTEST())                                

    {                                

        LOOPHEADER();                            

                                    

        ……                            

                                    

        /*                            

         * Was it the bgwriter?  Normal exit can be ignored; we'll start a new                            

         * one at the next iteration of the postmaster's main loop, if                            

         * necessary.  Any other exit condition is treated as a crash.                            

         */                            

        if (pid == BgWriterPID)                            

        {                            

            BgWriterPID = 0;                        

            if (!EXIT_STATUS_0(exitstatus))                        

                HandleChildCrash(pid, exitstatus,                    

                         _("background writer process"));            

            continue;                        

        }                            

                                    

        ……                            

    }                                

                                    

……                                    

}                                    

[作者：技术者高健@博客园  mail: [email protected] ]

由于我所使用的是 linux 平台，

[root@localhost postgresql-9.2.0]# find ./ -name "*.h"|xargs grep "HAVE_WAITPID"

./src/include/pg_config.h:#define HAVE_WAITPID 1
[root@localhost postgresql-9.2.0]#
所以，循环程序可以认为是：

while (((pid = waitpid(-1, &status, WNOHANG)) > 0))                                

{                                

    exitstatus = status;                            

                                

    ……                            

                                

    /*                            

     * Was it the bgwriter?  Normal exit can be ignored; we'll start a new                            

     * one at the next iteration of the postmaster's main loop, if                            

     * necessary.  Any other exit condition is treated as a crash.                            

     */                            

    if (pid == BgWriterPID)                            

    {                            

        BgWriterPID = 0;                        

        if (!(exitstatus==0))                        

            HandleChildCrash(pid, exitstatus,                    

                     _("background writer process"));            

        continue;                        

    }                            

                                

    ……                            

}                                

waitpid 用于监控子进程的结束。

其参数：

pid=-1 就是 等待任何子进程,相当于 wait()。

WNOHANG 就是  若pid指定的子进程没有结束，则waitpid()函数返回0，不予以等待。若结束，则返回该子进程的ID

而 HandleChildCrash 会完成重新建立子进程的工作。

[作者：技术者高健@博客园  mail: [email protected] ]

结束