[mpich-discuss] mpich problem.... net_send: could not write tofd=4, errno = 32

Luís Miranda luistm at gmail.com
Wed Feb 4 12:09:11 CST 2009


Ok. Thank you.

2009/2/4 Rajeev Thakur <thakur at mcs.anl.gov>

>  Can't say. You should hopefully get a better error message if you use
> MPICH2.
>
> Rajeev
>
>  ------------------------------
> *From:* mpich-discuss-bounces at mcs.anl.gov [mailto:
> mpich-discuss-bounces at mcs.anl.gov] *On Behalf Of *Luís Miranda
> *Sent:* Wednesday, February 04, 2009 11:30 AM
> *To:* mpich-discuss at mcs.anl.gov
> *Subject:* Re: [mpich-discuss] mpich problem.... net_send: could not write
> tofd=4, errno = 32
>
>  Could it possible be anything related with network. I'm running this on a
> cluster...
>
> 2009/2/4 Rajeev Thakur <thakur at mcs.anl.gov>
>
>>  Your code looks innocuous enough. Not sure why it should fail. I would
>> suggest using MPICH2 instead of MPICH-1. MPICH-1 is an old implementation
>> that is not actively supported.
>>
>> Rajeev
>>
>>  ------------------------------
>>  *From:* mpich-discuss-bounces at mcs.anl.gov [mailto:
>> mpich-discuss-bounces at mcs.anl.gov] *On Behalf Of *Luís Miranda
>> *Sent:* Wednesday, February 04, 2009 10:40 AM
>> *To:* mpich-discuss at mcs.anl.gov
>> *Subject:* [mpich-discuss] mpich problem.... net_send: could not write to
>> fd=4,errno = 32
>>
>>
>>
>>
>> Hi. I'm trying to run this:
>>  /opt/mpich/gnu/bin/mpirun -v -np 2    -machinefile program
>>
>> but i get this *error:*
>>
>> i'm process 0 de 2...
>> ROOT:  trying to send message...
>> p0_26706:  p4_error: interrupt SIGSEGV: 11
>> Killed by signal 2.
>> p0_26706: (0.113281) net_send: could not write to fd=4, errno = 32
>>
>>
>> *This is the code:*
>>
>> #include <stdio.h>
>> #include "mpi.h"
>>
>>
>> int main(int argc, char **argv){
>>
>>     int message,
>>         rank,
>>         size,
>>         i,
>>         tag = 0,
>>         namelen;
>>
>>     char processor_name[MPI_MAX_PROCESSOR_NAME];
>>
>>     MPI_Status status;
>>
>>     MPI_Init(&argc, &argv);
>>     MPI_Comm_rank(MPI_COMM_WORLD, &rank);
>>     MPI_Comm_size(MPI_COMM_WORLD, &size);
>>
>>     printf("i'm process %d de %d...\n", rank, size);
>>
>>     MPI_Barrier(MPI_COMM_WORLD);
>>
>>     if(rank == 0){
>>         message = 1;
>>         for (i=1; i<size; i++){
>>             printf("ROOT: trying to send message...\n");
>>             MPI_Ssend(&message, 1, MPI_INT, i, tag, MPI_COMM_WORLD);
>>
>>         }
>>     }else{
>>         printf("SLAVE %d: trying to receive message...\n", rank);
>>         MPI_Get_processor_name(processor_name,&namelen);
>>         MPI_Recv(&message, 1, MPI_INT, MPI_ANY_SOURCE, tag ,
>> MPI_COMM_WORLD, &status);
>>         printf("SLAVE %d MAQUINA %s: receive message %d\n ",rank,
>> processor_name, message);
>>     }
>>
>>     MPI_Finalize();
>>     return 0;
>> }
>>
>> *And this is my machine file:*
>>
>> beta.something.com
>> compute-1-0.local
>> compute-1-1.local
>> compute-1-2.local
>>
>> Any solution?
>>
>>
>> Thank you.
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20090204/90d1d140/attachment.htm>


More information about the mpich-discuss mailing list