// 这里注释也说到了，主要是杀死在同一个communicator的进程(不包括自己)

/*

 * Local helper function to build an array of all the procs in a

 * communicator, excluding this process.

 *

 * Killing a just the indicated peers must be implemented for

 * MPI_Abort() to work according to the standard language for

 * a 'high-quality' implementation.

 *

 * It would be nifty if we could differentiate between the

 * abort scenarios (but we don't, currently):

 *      - MPI_Abort()

 *      - MPI_ERRORS_ARE_FATAL

 *      - Victim of MPI_Abort()

 */

// 调用时传入了对应通信子

static void try_kill_peers(ompi_communicator_t *comm,

                           int errcode)

{

　　// 1. 第一部分: 给 ompi_process_name_t 指针申请空间，得到进程个数

    int nprocs;

    ompi_process_name_t *procs;

    nprocs = ompi_comm_size(comm);

    /* ompi_comm_remote_size() returns 0 if not an intercomm, so

       this is safe */

    nprocs += ompi_comm_remote_size(comm);

    procs = (ompi_process_name_t*) calloc(nprocs, sizeof(ompi_process_name_t));

    if (NULL == procs) {

        /* quick clean orte and get out */

        ompi_rte_abort(errno, "Abort: unable to alloc memory to kill procs");

    }

	// 2. 第二部分:	将进程放入数组中

    /* put all the local group procs in the abort list */

    int rank, i, count;

    rank = ompi_comm_rank(comm);	//这里可以获取到自己在该 communicator 中的 rank————疑问1

    for (count = i = 0; i < ompi_comm_size(comm); ++i) {

        if (rank == i) {

            /* Don't include this process in the array */

            --nprocs;

        } else {

            assert(count <= nprocs);

            procs[count++] =

                *OMPI_CAST_RTE_NAME(&ompi_group_get_proc_ptr(comm->c_remote_group, i, true)->super.proc_name);

        }

    }

	// 3. 第三部分: 远程的 group 进程也放入数组中

    /* if requested, kill off remote group procs too */

    for (i = 0; i < ompi_comm_remote_size(comm); ++i) {

        assert(count <= nprocs);

        procs[count++] =

            *OMPI_CAST_RTE_NAME(&ompi_group_get_proc_ptr(comm->c_remote_group, i, true)->super.proc_name);

    }

	// 4. 第四部分: 杀死进程

    if (nprocs > 0) {

        ompi_rte_abort_peers(procs, nprocs, errcode);

    }

    /* We could fall through here if ompi_rte_abort_peers() fails, or

       if (nprocs == 0).  Either way, tidy up and let the caller

       handle it. */

    free(procs);

}

#define ompi_rte_abort_peers(a, b, c) orte_errmgr.abort_peers(a, b, c)

/*

 * Module Structure

 */

struct orte_errmgr_base_module_2_3_0_t {

    /** Initialization Function */

    orte_errmgr_base_module_init_fn_t                       init;

    /** Finalization Function */

    orte_errmgr_base_module_finalize_fn_t                   finalize;

    orte_errmgr_base_module_log_fn_t                        logfn;

    orte_errmgr_base_module_abort_fn_t                      abort;

    orte_errmgr_base_module_abort_peers_fn_t                abort_peers;

};

typedef struct orte_errmgr_base_module_2_3_0_t orte_errmgr_base_module_2_3_0_t;

typedef orte_errmgr_base_module_2_3_0_t orte_errmgr_base_module_t;

ORTE_DECLSPEC extern orte_errmgr_base_module_t orte_errmgr;			//这是一个导出的extern全局变量

/*

 * Framework Interfaces

 */

/**

 * Module initialization function.

 *

 * @retval ORTE_SUCCESS The operation completed successfully

 * @retval ORTE_ERROR   An unspecifed error occurred

 */

typedef int (*orte_errmgr_base_module_init_fn_t)(void);

/**

 * Module finalization function.

 *

 * @retval ORTE_SUCCESS The operation completed successfully

 * @retval ORTE_ERROR   An unspecifed error occurred

 */

typedef int (*orte_errmgr_base_module_finalize_fn_t)(void);

/**

 * This is not part of any module so it can be used at any time!

 */

typedef void (*orte_errmgr_base_module_log_fn_t)(int error_code, char *filename, int line);

/**

 * Alert - self aborting

 * This function is called when a process is aborting due to some internal error.

 * It will finalize the process

 * itself, and then exit - it takes no other actions. The intent here is to provide

 * a last-ditch exit procedure that attempts to clean up a little.

 */

typedef void (*orte_errmgr_base_module_abort_fn_t)(int error_code, char *fmt, ...)

__opal_attribute_format_funcptr__(__printf__, 2, 3);

/**

 * Alert - abort peers

 *  This function is called when a process wants to abort one or more peer processes.

 *  For example, MPI_Abort(comm) will use this function to terminate peers in the

 *  communicator group before aborting itself.

 */

typedef int (*orte_errmgr_base_module_abort_peers_fn_t)(orte_process_name_t *procs,

                                                        orte_std_cntr_t num_procs,

                                                        int error_code);

 * (d) Error handling objects and operations

 *     1. void ompi_rte_abort(int err_code, char *fmt, ...) - Abort the current

 *        process with the specified error code and message.

 *     2. int ompi_rte_abort_peers(ompi_process_name_t *procs, size_t nprocs) -

 *        Abort the specified list of peers

 *     3. OMPI_ERROR_LOG(rc) - print error message regarding the given return code