Question

我有以下代码：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <mpi.h>

static int rank, size;

char msg[] = "This is a test message";

int main(int argc, char **argv) {
    MPI_Init(&argc, &argv);

    MPI_Comm_rank(MPI_COMM_WORLD, &rank);
    MPI_Comm_size(MPI_COMM_WORLD, &size);

    if (size != 2) {
        fprintf(stderr, "This test requires exactly 2 tasks (has: %d).\n", size);
        MPI_Finalize();
        return -1;
    }

    int run = 1;
    if (argc > 1) {
        run = atoi(argv[1]);
    }

    int len = strlen(msg) + 1;
    if (argc > 2) {
        len = atoi(argv[2]);
    }

    char buf[len];

    strncpy(buf, msg, len);

    MPI_Status statusArray[run];

    MPI_Request reqArray[run];


    double start = MPI_Wtime();

    for (int i = 0; i < run; i++) {
        if (!rank) {
          MPI_Isend(buf, len, MPI_CHAR, 1, 0, MPI_COMM_WORLD, &reqArray[i]);
          printf("mpi_isend for run %d\n", i);
        } else {
          MPI_Irecv(buf, len, MPI_CHAR, 0, 0, MPI_COMM_WORLD, &reqArray[i]);
          printf("mpi_irecv for run %d\n", i);
        }
    }
    int buflen = 512;
    char name[buflen];
    gethostname(name, buflen);
    printf("host: %s has rank %d\n", name, rank);
    printf("Reached here! for host %s before MPI_Waitall \n", name);
    if(!rank) {
      printf("calling mpi_waitall for sending side which is %s\n", name);
      MPI_Waitall(run, &reqArray[0], &statusArray[0]);
    }
    else {
      printf("calling mpi_waitall for receiving side which is %s\n", name);
      MPI_Waitall(run, &reqArray[0], &statusArray[0]);
    }
    printf("finished waiting! for host %s\n", name);
    double end = MPI_Wtime();
    if (!rank) {
      printf("Throughput: %.4f Gbps\n", 1e-9 * len * 8 * run / (end - start));
    }

    MPI_Finalize();
}

我在MPI_Waitall之前在发送方遇到了段错误。错误消息是：

[host1:27679] *** Process received signal ***
[host1:27679] Signal: Segmentation fault (11)
[host1:27679] Signal code: Address not mapped (1)
[host1:27679] Failing at address: 0x8
[host1:27679] [ 0] /lib64/libpthread.so.0() [0x3ce7e0f500]
[host1:27679] [ 1] /usr/lib64/openmpi/mca_btl_openib.so(+0x21dc7) [0x7f46695c1dc7]
[host1:27679] [ 2] /usr/lib64/openmpi/mca_btl_openib.so(+0x1cbe1) [0x7f46695bcbe1]
[host1:27679] [ 3] /lib64/libpthread.so.0() [0x3ce7e07851]
[host1:27679] [ 4] /lib64/libc.so.6(clone+0x6d) [0x3ce76e811d]
[host1:27679] *** End of error message ***

我认为MPI_Request的数组有问题。有人能指出来吗？谢谢！

Answer 1

我没有问题地运行你的程序（除了不包括unistd.h的警告）。问题可能与您的Open MPI设置有关。您使用的是具有InfiniBand网络的计算机吗？如果没有，您可能希望更改为仅使用默认的tcp实现。您的问题可能与此有关。

如果你想指定你只使用tcp，你应该这样运行：

mpirun --mca btl tcp,self -n 2 <prog_name> <prog_args>

这将确保不会意外地检测到openib并在不应该使用时使用它。

另一方面，如果您的意思是使用InfiniBand，您可能会发现Open MPI存在某些问题。我怀疑是这种情况，因为你没有做任何花哨的事情。

MPI_Waitall错误：地址未映射

1 个答案: