[Users] change the number of nodes on Cori

Erik Schnetter schnetter at cct.lsu.edu
Tue May 7 10:44:56 CDT 2019


Chia-Hui

Please go to <https://einsteintoolkit.org> and click the "report a bug"
button.

-erik


On Tue, May 7, 2019 at 11:00 AM 林家暉 <r06222015 at ntu.edu.tw> wrote:

> Dear Erik,
>
> I see . Could you tell me how to update a support ticket ?  I have no
> experience on that.
>
> Thank you.
>
> Best regards,
>
> Chia-Hui
> ------------------------------
> *寄件者:* Erik Schnetter <schnetter at cct.lsu.edu>
> *寄件日期:* 2019年5月7日 下午 10:53:08
> *收件者:* 林家暉
> *副本:* Einstein Toolkit Users
> *主旨:* Re: [Users] change the number of nodes on Cori
>
> Chia-Hui
>
> I think we need to update the submit script template for Cori. This will
> need to be done by someone with access to Cori. Please update a support
> ticket for this.
>
> -erik
>
>
> On Tue, May 7, 2019 at 10:50 AM 林家暉 <r06222015 at ntu.edu.tw> wrote:
>
>> Dear Erik,
>>
>> I resent the submit script.
>>
>> When I use "sqs" to check the status of my job, it is listed in the
>> following:
>>
>>
>>
>> NODES is 1 not 2, so I think only 1 node is used.
>>
>> Thanks.
>>
>>
>> Best regards,
>>
>> Chia-Hui
>> ------------------------------
>> *寄件者:* Erik Schnetter <schnetter at cct.lsu.edu>
>> *寄件日期:* 2019年5月7日 下午 10:44:53
>> *收件者:* 林家暉
>> *副本:* Einstein Toolkit Users
>> *主旨:* Re: [Users] change the number of nodes on Cori
>>
>> Chai-Hui
>>
>> Actually, the last line of the log file you posted says 'NODES': '2'.
>> Why do you think that your job is running on a single node only?
>>
>> -erik
>>
>> On Tue, May 7, 2019 at 10:42 AM Erik Schnetter <schnetter at cct.lsu.edu>
>> wrote:
>> >
>> > Chai-Hui
>> >
>> > You posted the submit script template that doesn't show how many nodes
>> > are requested. Can you instead post the submit script that has the
>> > number of processes etc. filled in? You will find it in the job's
>> > output directory in "output-0000/SIMFACTORY/SubmitScript".
>> >
>> > -erik
>> >
>> > On Tue, May 7, 2019 at 9:28 AM Erik Schnetter <schnetter at cct.lsu.edu>
>> wrote:
>> > >
>> > > Chai-Hui
>> > >
>> > > Your second command (using --procs 64) should request 2 nodes. If not,
>> > > there is an error in Cori's machine description. It could also be that
>> > > Cori's queuing options changed since the description was written. I
>> > > don't have access to Cori at the moment so I cannot check myself.
>> > >
>> > > Can you post the submit script that is generated for your job, as well
>> > > as the output of your job?
>> > >
>> > > -erik
>> > >
>> > > On Tue, May 7, 2019 at 2:20 AM 林家暉 <r06222015 at ntu.edu.tw> wrote:
>> > > >
>> > > > Hello,
>> > > >
>> > > > I use the nersc machine cori to run the ET simulaiton. I am
>> wondering how to change the number of nodes. I use the command like :
>> > > >
>> > > >  simfactory/bin/sim submit mysimulation --parfile par/file.par
>> --node 2 --walltime 00:30:00
>> > > >
>> > > >  simfactory/bin/sim submit mysimulation --parfile par/file.par
>> --procs 64 --walltime 00:30:00
>> > > >
>> > > >
>> > > > but neither of them change the node used from 1 to 2. Is there some
>> possible way to change the number of nodes?
>> > > > Thank you.
>> > > >
>> > > > Best regards,
>> > > > Chia-Hui
>> > > >
>> > > > _______________________________________________
>> > > > Users mailing list
>> > > > Users at einsteintoolkit.org
>> > > > http://lists.einsteintoolkit.org/mailman/listinfo/users
>> > >
>> > >
>> > >
>> > > --
>> > > Erik Schnetter <schnetter at cct.lsu.edu>
>> > > http://www.perimeterinstitute.ca/personal/eschnetter/
>> >
>> >
>> >
>> > --
>> > Erik Schnetter <schnetter at cct.lsu.edu>
>> > http://www.perimeterinstitute.ca/personal/eschnetter/
>>
>>
>>
>> --
>> Erik Schnetter <schnetter at cct.lsu.edu>
>> http://www.perimeterinstitute.ca/personal/eschnetter/
>>
>
>
> --
> Erik Schnetter <schnetter at cct.lsu.edu>
> http://www.perimeterinstitute.ca/personal/eschnetter/
>
>

-- 
Erik Schnetter <schnetter at cct.lsu.edu>
http://www.perimeterinstitute.ca/personal/eschnetter/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.einsteintoolkit.org/pipermail/users/attachments/20190507/71aa597a/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ???? 2019-05-07 ??10.47.30.png
Type: image/png
Size: 38723 bytes
Desc: not available
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20190507/71aa597a/attachment-0001.png 


More information about the Users mailing list