[mpich-discuss] Unexpected results

"Antonio J. Peña" apenya at mcs.anl.gov
Thu Apr 2 20:09:31 CDT 2015


Hi Ken,

Please check that you have password-less ssh connectivity between the nodes.

Best,
   Antonio


On 04/02/2015 07:33 PM, Ken Miller wrote:
> Hello,
>
> I am hoping someone might be able to point out what I am doing wrong. 
> I have setup a Raspberry Pi cluster by going through a couple 
> tutorials. The last step is to use MPI to test the cluster. Everything 
> was going great until I ran the following command:
>
> mpiexec -f machinefile -n 4 hostname
>
> My machinefile contains the following:
>
> *pi at Pi01* *~/mpi_test $* cat machinefile
> 192.168.2.121
> 192.168.2.122
> 192.168.2.123
> 192.168.2.124
>
> But, when I run the mpiexec command, I get the following error:
>
> *pi at Pi01* *~/mpi_test $* mpiexec -f machinefile -n 4 hostname
> Pi01
> [mpiexec at Pi01] control_cb 
> (/home/pi/mpich2/mpich-3.1/src/pm/hydra/pm/pmiserv/pmiserv_cb.c:200): 
> assert (!closed) failed
> [mpiexec at Pi01] HYDT_dmxu_poll_wait_for_event 
> (/home/pi/mpich2/mpich-3.1/src/pm/hydra/tools/demux/demux_poll.c:76): 
> callback returned error status
> [mpiexec at Pi01] HYD_pmci_wait_for_completion 
> (/home/pi/mpich2/mpich-3.1/src/pm/hydra/pm/pmiserv/pmiserv_pmci.c:198): error 
> waiting for event
> [mpiexec at Pi01] main 
> (/home/pi/mpich2/mpich-3.1/src/pm/hydra/ui/mpich/mpiexec.c:336): 
> process manager error waiting for completion
> *pi at Pi01**~/mpi_test $*
>
> Clearly, I am missing something. Would appreciate any help in advance.
>
> Thanks.
>
> Ken
>
> ps. I am connected to the other Pis evident by the following ping 
> results. I can also log into each of the other 3 Pis.
>
> ping 192.168.2.122
> PING 192.168.2.122 (192.168.2.122) 56(84) bytes of data.
> 64 bytes from 192.168.2.122: icmp_req=1 ttl=64 time=0.807 ms
> 64 bytes from 192.168.2.122: icmp_req=2 ttl=64 time=0.626 ms
> 64 bytes from 192.168.2.122: icmp_req=3 ttl=64 time=0.614 ms
> 64 bytes from 192.168.2.122: icmp_req=4 ttl=64 time=0.605 ms
> 64 bytes from 192.168.2.122: icmp_req=5 ttl=64 time=0.603 ms
> ^C
> --- 192.168.2.122 ping statistics ---
> 5 packets transmitted, 5 received, 0% packet loss, time 4002ms
> rtt min/avg/max/mdev = 0.603/0.651/0.807/0.078 ms
> *pi at Pi01* *~/mpi_test $* ping 192.168.2.123
> PING 192.168.2.123 (192.168.2.123) 56(84) bytes of data.
> 64 bytes from 192.168.2.123: icmp_req=1 ttl=64 time=0.794 ms
> 64 bytes from 192.168.2.123: icmp_req=2 ttl=64 time=0.634 ms
> 64 bytes from 192.168.2.123: icmp_req=3 ttl=64 time=0.628 ms
> 64 bytes from 192.168.2.123: icmp_req=4 ttl=64 time=0.607 ms
> ^C
> --- 192.168.2.123 ping statistics ---
> 4 packets transmitted, 4 received, 0% packet loss, time 3003ms
> rtt min/avg/max/mdev = 0.607/0.665/0.794/0.081 ms
> *pi at Pi01* *~/mpi_test $* ping 192.168.2.124
> PING 192.168.2.124 (192.168.2.124) 56(84) bytes of data.
> 64 bytes from 192.168.2.124: icmp_req=1 ttl=64 time=0.787 ms
> 64 bytes from 192.168.2.124: icmp_req=2 ttl=64 time=0.632 ms
> 64 bytes from 192.168.2.124: icmp_req=3 ttl=64 time=0.612 ms
> ^C
> --- 192.168.2.124 ping statistics ---
> 3 packets transmitted, 3 received, 0% packet loss, time 2002ms
> rtt min/avg/max/mdev = 0.612/0.677/0.787/0.078 ms
> *pi at Pi01**~/mpi_test $*
>
>
> _______________________________________________
> discuss mailing list     discuss at mpich.org
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/discuss


-- 
Antonio J. Peña
Postdoctoral Appointee
Mathematics and Computer Science Division
Argonne National Laboratory
9700 South Cass Avenue, Bldg. 240, Of. 3148
Argonne, IL 60439-4847
apenya at mcs.anl.gov
www.mcs.anl.gov/~apenya

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20150402/1197fa9e/attachment.html>
-------------- next part --------------
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss


More information about the discuss mailing list