[Wien] I still have problem with wienk in parallel mode

[Nilton]

Ok, thank very much for all suggestions..
Nilton

2012/1/6 Laurence Marks <L-marks at northwestern.edu>

> A guess, which is the best we can do at the moment. See if you can ssh
> into the nodes without the ".local" at the end and if you can then create a
> .machines file without the .local and try x lapw1 -c -p.
>
> If you have access to the dns files also try aliasing the nodes to, for
> instance, c0, c1 etc and use these in .machines.
>
> The fact that your .machine1 file is empty is wrong, and suggests
> something has gone wrong. It may be because of the "." in your names
> leading to some sed problems, but this is just my guess.
>
> ---------------------------
>
> Professor Laurence Marks
> Department of Materials Science and Engineering
> Northwestern University
> www.numis.northwestern.edu 1-847-491-3996
> "Research is to see what everybody else has seen, and to think what nobody
> else has thought"
> Albert Szent-Gyorgi
>  On Jan 6, 2012 2:58 PM, "Nilton" <nilton.dantas at gmail.com> wrote:
>
>> Dear fellows,
>> thanks for the answers.
>>
>>
>> 2012/1/2 Peter Blaha <pblaha at theochem.tuwien.ac.at>
>>
>>>  model name      : Intel(R) Xeon(R) CPU           X3430  @ 2.40GHz
>>>> stepping        : 5
>>>> cpu MHz         : 1197.000
>>>>
>>>
>>> Are you running at half speed ???
>>> At least on my machines it would indicate the expected cpu MHz of 2400
>>
>>
>> the machine was idle when I got this information. If I repeat with lapw1
>> submited the speed goes to double.In principle this message should give you
>> some clues.
>>
>>
>>> The mpirun command you listed is incomplete and wrong. You said you have:
>>>
>>> setenv WIEN_MPIRUN "mpirun -v -np _NP_ -machinefile _HOSTS_ _EXEC_"
>>>
>>> I think  the "-v" is wrong ??
>>>
>> It is correct. it means verbose mode as you can see here
>>
>>
>> ---------------------------------------------------------------------------------------------------------------------------------------
>> [nilton at bodesking case]$ mpirun -v -np 4 -machinefile .machines
>> /home/nilton/wien2k/lapw1c_mpi lapw1.def
>> running /home/nilton/wien2k/lapw1c_mpi on 4 LINUX ch_p4 processors
>> Created
>> /home/nilton/pesquisa/dftCalc/calWien/gaxtl1-xas/075/case/case/PI13830
>>
>> -------------------------------------------------------------------------------------------------------------------------------------
>> I am using .machines because .machine1 is empty.
>> I tried this command and it works very well, as you can see in the output
>> of top command
>>
>> --------------------------------------------------------lapw1c_mpi runnig
>> in bodeking
>> [nilton at bodesking ~]$ top
>>
>> top - 17:41:40 up  2:31,  6 users,  load average: 0.42, 0.99, 1.91
>> Tasks: 201 total,   2 running, 199 sleeping,   0 stopped,   0 zombie
>> Cpu(s):  8.7%us,  1.1%sy,  0.0%ni, 85.8%id,  0.0%wa,  0.1%hi,  4.4%si,
>> 0.0%st
>> Mem:  12250640k total,  1639948k used, 10610692k free,   137816k buffers
>> Swap:  8193140k total,        0k used,  8193140k free,   879624k cached
>>
>>   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
>> COMMAND
>> 14711 nilton    16   0 47540  22m 3220 R 35.2  0.2   0:13.03 lapw1c_mpi
>>
>>
>>
>> ---------------------------------------------------------------------------------------------------------------
>>
>>
>> -----------------------lapw1c_mpi running in comput-0-0------------
>> [nilton at compute-0-1 ~]$ top
>>
>> top - 17:42:38 up 4 days,  3:34,  2 users,  load average: 0.41, 0.91, 2.08
>> Tasks: 115 total,   2 running, 113 sleeping,   0 stopped,   0 zombie
>> Cpu(s):  6.2%us,  0.7%sy,  0.0%ni, 88.2%id,  0.0%wa,  0.6%hi,  4.3%si,
>> 0.0%st
>> Mem:   6058240k total,  3244748k used,  2813492k free,   207132k buffers
>> Swap:  1020116k total,        0k used,  1020116k free,  2881356k cached
>>
>>   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
>> COMMAND
>> 17044 nilton    16   0 65288  34m 3204 R 29.3  0.6   0:30.33
>> lapw1c_mpi
>>
>>
>> and by the way the time program is instaled as you can see below
>>
>> [nilton at bodesking case]$ time
>>
>> real    0m0.000s
>> user    0m0.000s
>> sys     0m0.000s
>>
>> Nilton
>> --
>> Nilton S. Dantas
>> Universidade Estadual de Feira de Santana
>> Departamento de Ciências Exatas
>> Área de Informática
>> Av. Transnordestina, S/N, Bairro Novo Horizonte
>> CEP 44036900 - Feira de Santana, Bahia, Brasil
>> Tel./Fax +55 75 31618086
>> http://www2.ecomp.uefs.br/ <http://www.uefs.br/portal>
>>
>>
>> _______________________________________________
>> Wien mailing list
>> Wien at zeus.theochem.tuwien.ac.at
>> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>>
>>
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>
>


-- 
Nilton S. Dantas
Universidade Estadual de Feira de Santana
Departamento de Ciências Exatas
Área de Informática
Av. Transnordestina, S/N, Bairro Novo Horizonte
CEP 44036900 - Feira de Santana, Bahia, Brasil
Tel./Fax +55 75 31618086
http://www2.ecomp.uefs.br/ <http://www.uefs.br/portal>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://zeus.theochem.tuwien.ac.at/pipermail/wien/attachments/20120110/13f194c4/attachment.htm>