OpenMPI源码剖析2：ompi_mpi_errors_are_fatal_comm_handler函数

上一篇文章说道，初始化失败会有一个函数调用:

ompi_mpi_errors_are_fatal_comm_handler(NULL, NULL, message);

所以这里简单地进入了 ompi_mpi_errors_are_fatal_comm_handler 函数:
看到其头文件 errhandler_predefined.h :

#ifndef OMPI_ERRHANDLER_PREDEFINED_H
#define OMPI_ERRHANDLER_PREDEFINED_H
 
#include "ompi_config.h"
 
struct ompi_communicator_t;
struct ompi_file_t;
struct ompi_win_t;
 
/**
 * Handler function for MPI_ERRORS_ARE_FATAL								//---------------看到了吗？fatal_error
 */
OMPI_DECLSPEC void ompi_mpi_errors_are_fatal_comm_handler(struct ompi_communicator_t **comm,
					    int *error_code, ...);
OMPI_DECLSPEC void ompi_mpi_errors_are_fatal_file_handler(struct ompi_file_t **file,
					    int *error_code, ...);
OMPI_DECLSPEC void ompi_mpi_errors_are_fatal_win_handler(struct ompi_win_t **win,
					    int *error_code, ...);
 
/**
 * Handler function for MPI_ERRORS_RETURN									//---------------- error_return
 */
OMPI_DECLSPEC void ompi_mpi_errors_return_comm_handler(struct ompi_communicator_t **comm,
                                   int *error_code, ...);
OMPI_DECLSPEC void ompi_mpi_errors_return_file_handler(struct ompi_file_t **file,
                                   int *error_code, ...);
OMPI_DECLSPEC void ompi_mpi_errors_return_win_handler(struct ompi_win_t **win,
                                   int *error_code, ...);
 
#endif /* OMPI_ERRHANDLER_PREDEFINED_H */

　跳去它的实现文件 errhandler_predefined.c 中看对应函数:　

void ompi_mpi_errors_are_fatal_comm_handler(struct ompi_communicator_t **comm,
                                            int *error_code, ...)
{
  char *name;
  struct ompi_communicator_t *abort_comm;
  va_list arglist;
 
  va_start(arglist, error_code);
 
  if (NULL != comm) {
      name = (*comm)->c_name;
      abort_comm = *comm;
  } else {
      name = NULL;
      abort_comm = NULL;
  }
  backend_fatal("communicator", abort_comm, name, error_code, arglist);
  va_end(arglist);
}

　映入眼帘的是  ompi_communicator_t 类，MPI中的通信子应该就是通过这个类来实现的，后期要重点学习

这里涉及到不变参数列表的知识，参考此处:  http://www.cnblogs.com/hanyonglu/archive/2011/05/07/2039916.html

放到此处的具体场景，也就是arglist只有message一个变量，其实也就是:

static const char FUNC_NAME[] = "MPI_Init";

这里做了一些处理之后，调用 backend_fatal 函数，这是在本文件中的一个局部函数, 它做了什么呢？ :

static void backend_fatal(char *type, struct ompi_communicator_t *comm,
                          char *name, int *error_code,
                          va_list arglist)
{
    /* We only want aggregation while the rte is initialized */
    if (ompi_rte_initialized) {
        backend_fatal_aggregate(type, comm, name, error_code, arglist);
    } else {
        backend_fatal_no_aggregate(type, comm, name, error_code, arglist);
    }
 
    /* In most instances the communicator will be valid. If not, we are either early in
     * the initialization or we are dealing with a window. Thus, it is good enough to abort
     * on MPI_COMM_SELF, the error will propagate.
     */
    if (comm == NULL) {
        comm = &ompi_mpi_comm_self.comm;
    }
 
    if (NULL != error_code) {
        ompi_mpi_abort(comm, *error_code);
    } else {
        ompi_mpi_abort(comm, 1);
    }
}

　　backend_fatal_aggregate 函数是和聚合有关的，我们先跳过。————留下疑点1

因为我们传入的 error_code 参数为NULL， 最后程序会进入  ompi_mpi_abort(comm, 1);

它在 mpiruntime.h 头文件中，实现在 ompi_mpi_abort.c 文件中，贴上它的函数定义代码:

// 目前传入的参数是:   &ompi_mpi_comm_self.comm, 1
int
ompi_mpi_abort(struct ompi_communicator_t* comm,
               int errcode)
{
　　// 1. 我们要看的第一部分代码： 防止递归，获取节点名称
    char *host, hostname[OPAL_MAXHOSTNAMELEN];
    pid_t pid = 0;
 
    /* Protection for recursive invocation */
    if (have_been_invoked) {
        return OMPI_SUCCESS;
    }
    have_been_invoked = true;
 
    /* If MPI is initialized, we know we have a runtime nodename, so
       use that.  Otherwise, call gethostname. */
　　// 疑问2: rte到底是什么？这个估计后续的深入了解会接触的更多,可能是runtime environment
    if (ompi_rte_initialized) {
　　　　// host代表的也就是rank, 存储在 ompi_process_info 这个结构体中， ————疑问3
        host = ompi_process_info.nodename;
    } else {
        gethostname(hostname, sizeof(hostname));
        host = hostname;
    }
    pid = getpid();

　  // 2. 我们要看的第二部分代码: 打印函数调用堆栈
    /* Should we print a stack trace?  Not aggregated because they
       might be different on all processes. */
    if (opal_abort_print_stack) {
        char **messages;
        int len, i;
 
        if (OPAL_SUCCESS == opal_backtrace_buffer(&messages, &len)) {
            for (i = 0; i < len; ++i) {
                fprintf(stderr, "[%s:%d] [%d] func:%s\n", host, (int) pid,
                        i, messages[i]);
                fflush(stderr);
            }
            free(messages);
        } else {
            /* This will print an message if it's unable to print the
               backtrace, so we don't need an additional "else" clause
               if opal_backtrace_print() is not supported. */
            opal_backtrace_print(stderr, NULL, 1);
        }
    }

　　// 3. 第三部分代码: abort之前的自旋等待
    /* Should we wait for a while before aborting? */
 
    if (0 != opal_abort_delay) {
        if (opal_abort_delay < 0) {
            fprintf(stderr ,"[%s:%d] Looping forever (MCA parameter opal_abort_delay is < 0)\n",
                    host, (int) pid);
            fflush(stderr);
            while (1) {
                sleep(5);
            }
        } else {
            fprintf(stderr, "[%s:%d] Delaying for %d seconds before aborting\n",
                    host, (int) pid, opal_abort_delay);
            do {
                sleep(1);
            } while (--opal_abort_delay > 0);
        }
    }
　　 
　　// 4. 第四部分: RTE未初始化的情况下，看ompi_mpi_finalized的情况是哪种

    /* If the RTE isn't setup yet/any more, then don't even try
       killing everyone.  Sorry, Charlie... */
    if (!ompi_rte_initialized) {
        fprintf(stderr, "[%s:%d] Local abort %s completed successfully, but am not able to aggregate error messages, and not able to guarantee that all other processes were killed!\n",
                host, (int) pid, ompi_mpi_finalized ?
                "after MPI_FINALIZE started" : "before MPI_INIT completed");
        _exit(errcode == 0 ? 1 : errcode);
    }

　　 // 5.第五部分: 有了communicator, 干掉进程集————疑问4:那是不是说，如果有一个进程初始化失败，整个进程集都会挂掉呢？
    /* If OMPI is initialized and we have a non-NULL communicator,
       then try to kill just that set of processes */
    if (ompi_mpi_initialized && !ompi_mpi_finalized && NULL != comm) {
        try_kill_peers(comm, errcode);　　　　　　// 疑问 5
    }

　　// 6. 第六部分: 很少情况会执行到这里，abort运行环境
    /* We can fall through to here in a few cases:
 
       1. The attempt to kill just a subset of peers via
          try_kill_peers() failed (e.g., as of July 2014, ORTE does
          returns NOT_IMPLENTED from orte_rte_abort_peers()).
       2. MPI wasn't initialized, was already finalized, or we got a
          NULL communicator.
 
       In all of these cases, the only sensible thing left to do is to
       kill the entire job.  Wah wah. */
    ompi_rte_abort(errcode, NULL);　　　　　　　　//疑问 6
 
    /* Does not return */
}　　

为了章节结构好看，本篇就到此，留下6个疑问，再次重申一下:

1. backend_fatal_aggregate 函数

2: rte到底是什么？这个估计后续的深入了解会接触的更多,可能是runtime environment

3. host代表的也就是rank, 存储在 ompi_process_info 这个结构体中

4.那是不是说，如果有一个进程初始化失败，整个进程集都会挂掉呢？

5. try_kill_peers 函数

6. ompi_rte_abort 函数