Bart,
It looks like a bug that involves the osc/rdma component.
Meanwhile, you can
mpirun --mca osc ^rdma ...
Cheers,
Gilles
On Sat, Feb 16, 2019 at 8:43 PM b...@bartjanssens.org
wrote:
>
> Hi,
>
> Running the following test code on two processes:
>
> #include
> #include
> #include
>
> #define N 2
>
> int main(int argc, char **argv)
> {
> int i, rank, num_procs, len, received[N], buf[N];
> MPI_Aint addrbuf[1], recvaddr[1];
> MPI_Win win, awin;
>
> MPI_Init(, );
> MPI_Comm_rank(MPI_COMM_WORLD, );
> MPI_Comm_size(MPI_COMM_WORLD, _procs);
>
> MPI_Win_create_dynamic(MPI_INFO_NULL, MPI_COMM_WORLD, );
> MPI_Win_attach(win, buf, sizeof(int)*N);
> MPI_Win_create(addrbuf, sizeof(MPI_Aint), sizeof(MPI_Aint), MPI_INFO_NULL,
> MPI_COMM_WORLD, );
>
> MPI_Win_lock(MPI_LOCK_EXCLUSIVE, rank, 0, awin);
> MPI_Get_address(buf, [0]);
> MPI_Win_unlock(rank,awin);
>
> if(rank == 0)
> {
> printf("Process %d is waiting for debugger attach\n", getpid());
> sleep(15);
> }
>
> MPI_Barrier(MPI_COMM_WORLD);
>
> if(rank == 0)
> {
> for(int r = 0; r != N; ++r)
> {
> MPI_Win_lock(MPI_LOCK_EXCLUSIVE, r, 0, awin);
> MPI_Get(recvaddr, 1, MPI_AINT, r, 0, 1, MPI_AINT, awin);
> MPI_Win_unlock(r, awin);
> MPI_Win_lock(MPI_LOCK_EXCLUSIVE, r, 0, win);
> MPI_Get(received, N, MPI_INT, r, recvaddr[0], N, MPI_INT, win);
> printf("First value from %d is %d\n", r, received[0]);
> MPI_Win_unlock(r, win);
> }
> }
>
> MPI_Barrier(MPI_COMM_WORLD);
>
> MPI_Win_free();
> MPI_Finalize();
> return 0;
> }
>
>
> results in a crash with this backtrace (starting at the second MPI_Get line
> in my code above):
>
> #0 mca_btl_vader_get_cma (btl=0x7f44888d0220 , endpoint=0x0,
> local_address=0x74a13c18, remote_address=,
> local_handle=0x0,
> remote_handle=, size=8, flags=0, order=255,
> cbfunc=0x7f4488231250 , cbcontext=0x555d01e1c060,
> cbdata=0x0) at btl_vader_get.c:95
> #1 0x7f44882308c1 in ompi_osc_rdma_get_contig
> (sync=sync@entry=0x555d01e1be90, peer=peer@entry=0x555d01e16f10,
> source_address=,
> source_address@entry=140737297595424,
> source_handle=source_handle@entry=0x7f448a747180, target_buffer= out>, target_buffer@entry=0x74a13c18, size=size@entry=8,
> request=) at osc_rdma_comm.c:698
> #2 0x7f44882354b6 in ompi_osc_rdma_master (alloc_reqs=true,
> rdma_fn=0x7f4488230610 , max_rdma_len= out>, request=0x555d01e1c060,
> remote_datatype=0x555d0004a2c0 , remote_count= out>, remote_handle=0x7f448a747180, remote_address=,
> peer=,
> local_datatype=0x555d0004a2c0 , local_count= out>, local_address=0x74a13c18, sync=0x555d01e1be90) at
> osc_rdma_comm.c:349
> #3 ompi_osc_rdma_get_w_req (request=0x0, source_datatype=0x555d0004a2c0
> , source_count=, source_disp=,
> peer=,
> origin_datatype=0x555d0004a2c0 , origin_count= out>, origin_addr=0x74a13c18, sync=0x555d01e1be90) at osc_rdma_comm.c:803
> #4 ompi_osc_rdma_get (origin_addr=0x74a13c18, origin_count= out>, origin_datatype=0x555d0004a2c0 , source_rank= out>,
> source_disp=, source_count=,
> source_datatype=0x555d0004a2c0 , win=0x555d01e0aae0) at
> osc_rdma_comm.c:880
> #5 0x7f448b404b6b in PMPI_Get (origin_addr=0x74a13c18,
> origin_count=2, origin_datatype=0x555d0004a2c0 ,
> target_rank=,
> target_disp=, target_count=,
> target_datatype=0x555d0004a2c0 , win=0x555d01e0aae0) at
> pget.c:81
> #6 0x555d00047430 in main (argc=1, argv=0x74a13d18) at
> onesided_crash_report.c:41
>
> On OpenMPI 3.1.3 the code works fine. Am I doing something wrong, or is this
> a bug?
>
> Kind regards,
>
> Bart ___
> users mailing list
> users@lists.open-mpi.org
> https://lists.open-mpi.org/mailman/listinfo/users
___
users mailing list
users@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/users
