[mpich-discuss] Error Running MPICH for Photochemical Modeling

[Sarika K]

Hi Abhishek:


We had a similar issue and was fixed when the following were set as root by
our sys admin.

# NOTE: "Unlimited" is not truly unlimited.  It

# will set the given limit to the maximum value

# determined by your hardware configuration

ulimit -t unlimited              # cputime

   ulimit -f unlimited              # filesize

   ulimit -d unlimited              # datasize

   ulimit -s unlimited              # stacksize

   ulimit -c unlimited              # coredumpsize

   ulimit -m unlimited              # memoryuse

   ulimit -v unlimited              # vmemoryuse

   ulimit -n unlimited              # descriptors

   ulimit -l unlimited              # memorylocked

   ulimit -u unlimited              # maxproc


Hope this helps,

Sarika


On Wed, Sep 17, 2014 at 11:04 AM, Balaji, Pavan <balaji at anl.gov> wrote:

>
> On Sep 17, 2014, at 1:00 PM, Abhishek Bhat <abhat at trinityconsultants.com>
> wrote:
> > The application works when there is a less resource intensive runs
> (larger grid with larger grid spacing).  The issue occurs when we have
> nested grid runs.  Also the application works without any issues for less
> than 7 processes (1 I/O and 6 nodes).
>
> That’s not an indication that the application is correct with more
> processes.  Many applications work at smaller scales but fail at larger
> scals.  From the error, the indications point to the application.  I’d
> recommend digging into the application and figuring out what’s breaking.
> The -print-all-exitcodes that Sangmin suggested, or attaching a debugger
> might be useful for this.
>
>   — Pavan
>
> --
> Pavan Balaji  ✉️
> http://www.mcs.anl.gov/~balaji
>
> _______________________________________________
> discuss mailing list     discuss at mpich.org
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/discuss
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20140917/53206f08/attachment.html>
-------------- next part --------------
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss