[mpich-discuss] MPI_Barrier(MPI_COMM_WORLD) failed

[Gauri Kulkarni]

Hi,

I have no experience with MPICH, but just want to chip in. Recently, I got
errors like these as well (may not be related, but still). The solution - or
rather resolution - that I found from discussion here is my version of
MPICH2 is configured to be used with SLURM, meaning, the process manager is
slurm. If I start an mpd and run the program that is compiled with my
version of MPICH2, then I get these errors. What process manager are you
using?

mpiexec -np 2 ./helloworld.mympi


Fatal error in MPI_Finalize: Other MPI error, error stack:
MPI_Finalize(255)...................: MPI_Finalize failed
MPI_Finalize(154)...................:
MPID_Finalize(94)...................:
MPI_Barrier(406)....................: MPI_Barrier(comm=0x44000002) failed
MPIR_Barrier(77)....................:
MPIC_Sendrecv(120)..................:
MPID_Isend(103).....................: failure occurred while attempting to
send an eager message
MPIDI_CH3_iSend(172)................:
MPIDI_CH3I_VC_post_sockconnect(1090):
MPIDI_PG_SetConnInfo(615)...........: PMI_KVS_Get failedStatus of MPI_Init =
0 Status of MPI_Comm_Rank = 0 Status of MPI_Comm_Size = 0 Hello world! I'm 1
of 2 on n53
Fatal error in MPI_Finalize: Other MPI error, error stack:
MPI_Finalize(255)...................: MPI_Finalize failed
MPI_Finalize(154)...................:
MPID_Finalize(94)...................:
MPI_Barrier(406)....................: MPI_Barrier(comm=0x44000002) failed
MPIR_Barrier(77)....................:
MPIC_Sendrecv(120)..................:
MPID_Isend(103).....................: failure occurred while attempting to
send an eager message
MPIDI_CH3_iSend(172)................:
MPIDI_CH3I_VC_post_sockconnect(1090):
MPIDI_PG_SetConnInfo(615)...........: PMI_KVS_Get failedStatus of MPI_Init =
0 Status of MPI_Comm_Rank = 0 Status of MPI_Comm_Size = 0 Hello world! I'm 0
of 2 on n53

Gauri.
---------


On Mon, Apr 20, 2009 at 11:20 AM, Xiao Bo Lu <xiao.lu at auckland.ac.nz> wrote:

> Hi all,
>
> I've recently installed MPICH2-1.0.8 on my local machine (x86_64 Linux,
> gfortran 4.1.2) and I am now experiencing errors with my mpi code. The error
> messages are:
>
> Fatal error in MPI_Barrier: Other MPI error, error stack:
> MPI_Barrier(406)..........................: MPI_Barrier(MPI_COMM_WORLD)
> failed
> MPIR_Barrier(77)..........................:
> MPIC_Sendrecv(126)........................:
> MPIC_Wait(270)............................:
> MPIDI_CH3i_Progress_wait(215).............: an error occurred while
> handling an event returned by MPIDU_Sock_Wait()
> MPIDI_CH3I_Progress_handle_sock_event(420):
> MPIDU_Socki_handle_read(637)..............: connection failure
> (set=0,sock=1,errno=104:Connection reset by peer)[cli_0]: aborting job:
> Fatal error in MPI_Barrier: Other MPI error, error stack:
> MPI_Barrier(406)..........................: MPI_Barrier(MPI_COMM_WORLD)
> failed
> MPIR_Barrier(77)..........................:
> MPIC_Sendrecv(126)........................:
> MPIC_Wait(270)............................:
> MPIDI_CH3i_Progress_wait(215).............: an error occurred while
> handling an event returned by MPIDU_Sock_Wait()
> MPIDI_CH3I_Progress_handle_sock_event(420):
> MPIDU_Socki_handle_read size of processor is:                    4
>
> I searched the net and found quite a few links about such error, but none
> of the posts could give a definitive fix. Do some of you know what could
> cause this error (e.g. incorrect installation; environmental setting..) and
> how to fix it?
>
> Regards
> Xiao
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20090421/b1beabd7/attachment.htm>