July 2014 - mpi-comments - mailman3.cels.anl.gov

Re: [Mpi-comments] error message while I tried to do a parallel job on a cluster
by Terry Pang 30 Jul '14

30 Jul '14

Hi Chun, I had this problem same as you and this is how I solved it. I unsure my method will work for you. I found that my source code example, mympi.c and makefile must have the same location in slaves computers too else it keep showing this error. Then compile them (in slaves too), master and slaves will get the executable file. When run the executable file from master, slaves will detect the execution code you typed from master and run the executable file. Hope this works for you. Good luck!!Thank You. Regards,Terry Pang Date: Tue, 29 Jul 2014 17:35:16 -0700 From: miracle.chun.2010(a)gmail.com To: mpi-comments(a)lists.mpi-forum.org Subject: [Mpi-comments] error message while I tried to do a parallel job on a cluster Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here:[mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed[mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra?And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them?Is there anyone who can give me some hint? Thanks a lot! Best,Chun _______________________________________________ mpi-comments mailing list mpi-comments(a)lists.mpi-forum.org http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments

1 0

Re: [Mpi-comments] hydra problem ?
by Bland, Wesley B. 29 Jul '14

29 Jul '14

This mailing list is for commenting on the MPI Standard. Not for asking questions about using MPI. You should direct your question to the mailings list for your implementation (discuss(a)mpich.org<mailto:[email protected]>). On Jul 29, 2014, at 7:45 PM, "Chun Meng" <miracle.chun.2010(a)gmail.com<mailto:[email protected]>> wrote: Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here: [mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed [mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra? And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them? Is there anyone who can give me some hint? Thanks a lot! Best, Chun _______________________________________________ mpi-comments mailing list mpi-comments(a)lists.mpi-forum.org<mailto:[email protected]> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments

1 0

hydra problem ?
by Chun Meng 29 Jul '14

29 Jul '14

Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here: [mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed [mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra? And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them? Is there anyone who can give me some hint? Thanks a lot! Best, Chun

1 0

error message while I tried to do a parallel job on a cluster
by Chun Meng 29 Jul '14

29 Jul '14

Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here: [mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed [mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra? And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them? Is there anyone who can give me some hint? Thanks a lot! Best, Chun

1 0