Re: [ESPResSo] parallel computing

[Olaf Lenz]

This message is not caused by ESPResSo, but by your MPI implementation 
(OPENMPI?).To get rid of the messages, you will have to read openmpis manual.
Best regards Olaf 


"Mikheil Azatov" <address@hidden> schrieb:

>Hi,
>
>I'm using a parallel computing cluster here in UMD to run the simulation on
>espresso. Usually when I run the code I get this kind of messages(see
>below). The code still runs and gives me the results, but the problem is
>that the more CPU's I use the more errors I get and the slower is the
>simulation which results in very slow performance sometime. I was wondering
>if anyone ever had similar problems and could help me out here.
>
>
>[0,2,0]: OpenIB on host compute-f17-2.deepthought.umd.edu was unable to find
>any HCAs.
>Another transport will be used instead, although this may result in
>lower performance.
>
>
>libibverbs: Warning: RLIMIT_MEMLOCK is 32768 bytes.
>    This will severely limit memory registrations.
>
>0: Script directory:
>/software/dt-sw0/espresso/2.2.0b-custom/sys/lib/espresso/scripts
>[compute-f17-2.deepthought.umd.edu:08426] [0,0,0] ORTE_ERROR_LOG: Resource
>busy in file base/pls_base_receive.c at line 127
>0: Script directory:
>/software/dt-sw0/espresso/2.2.0b-custom/sys/lib/espresso/scripts
>0: Script directory:
>/software/dt-sw0/espresso/2.2.0b-custom/sys/lib/espresso/scripts
>[compute-f17-2.deepthought.umd.edu:08426] [0,0,0] ORTE_ERROR_LOG: Resource
>busy in file base/pls_base_receive.c at line 127
>[compute-f17-2.deepthought.umd.edu:08426] [0,0,0] ORTE_ERROR_LOG: Resource
>busy in file base/pls_base_receive.c at line 127
>
>
>
>Thanks, Mike
>_______________________________________________
>ESPResSo mailing list
>address@hidden
>https://fias.uni-frankfurt.de/mailman/listinfo/espresso

-- 
Diese Nachricht wurde von meinem Android-Mobiltelefon mit K-9 Mail gesendet.