[mpich-discuss] error

[Pavan Balaji]

This typically means that the nodes are not able to "see" each other. 
Try out these tests:

1. Can you do an ssh from "ranjit" to "node01"?

2. Can you do an ssh from "node01" to "ranjit"?

3. Are *both* nodes listed in the /etc/hosts file on *each* node?

4. Is the firewall on both nodes disabled?

I've added a FAQ entry for this problem: 
http://wiki.mcs.anl.gov/mpich2/index.php/Frequently_Asked_Questions#Q:_My_MPI_program_aborts_with_an_error_saying_it_cannot_communicate_with_other_processes

  -- Pavan

On 01/31/2011 05:54 AM, Ranjit Thapa wrote:
> Dear all,
> I found an error message, when i give the command
>
> mpiexec -hosts ranjit,node01 -n 4 ./examples/cpi
>
>
>
> Process 0 of 4 is on ranjit
> Process 2 of 4 is on ranjit
> Fatal error in PMPI_Bcast: Other MPI error, error stack:
> PMPI_Bcast(1306)......................: MPI_Bcast(buf=0x7fff8a02ebb8,
> count=1, MPI_INT, root=0, MPI_COMM_WORLD) failed
> MPIR_Bcast_impl(1150).................:
> MPIR_Bcast_intra(990).................:
> MPIR_Bcast_scatter_ring_allgather(840):
> MPIR_Bcast_binomial(187)..............:
> MPIC_Send(66).........................:
> MPIC_Wait(528)........................:
> MPIDI_CH3I_Progress(335)..............:
> MPID_nem_mpich2_blocking_recv(906)....:
> MPID_nem_tcp_connpoll(1830)...........: Communication error with rank 1:
> Process 1 of 4 is on node01
> Process 3 of 4 is on node01
> APPLICATION TERMINATED WITH THE EXIT STRING: Hangup (signal 1)
>
> What is the problem?
>
> Thanks in advance
>
> --
> Ranjit Thapa
> Research Associate
> Materials Simulation Lab.
> Department of Materials Science
> Indian Association for the Cultivation of Science
> KOL-700032
> Mobile No: +91 9593936060, +91 9804101030
> http://sites.google.com/site/ranjitphy/home
>
>
>
> _______________________________________________
> mpich-discuss mailing list
> mpich-discuss at mcs.anl.gov
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss

-- 
Pavan Balaji
http://www.mcs.anl.gov/~balaji