MPI Failure at line 839 of nonblocking.c (MPI_File_write_all : MPI_ERR_IO: input/output error)

[Jim Edwards]

Oh  - I should also mention that the result of this error is a hang and not
a clean abort.

On Wed, Aug 8, 2012 at 2:31 PM, Jim Edwards <jedwards at ucar.edu> wrote:

> I have my buffer limit set to 100MB so the maximum is well below 2GB
> and I see that the location of the error with respect to my code varies as
> I vary this limit.
>
>
>
> On Wed, Aug 8, 2012 at 2:27 PM, Rob Latham <robl at mcs.anl.gov> wrote:
>
>> On Wed, Aug 08, 2012 at 02:17:19PM -0600, Jim Edwards wrote:
>> > I am getting this error from parallel-netcdf using openmpi 1.4.5 and
>> intel
>> > 12.1.4 and a lustre filesystem.   Because this is
>> > non-blocking I am having a lot of difficulty pinpointing the issue, do
>> you
>> > have any suggestions?  I buffer multiple variables before
>> > calling the nfmpi_wait_all and if I turn off this buffering
>> functionality
>> > it appears to work fine.     All of this functionality works on several
>> > other systems so I
>> > think that it must be an issue lower in the software stack.
>>
>> How much data are you working on in total?   Sometimes this
>> "MPI_ERR_IO: input/output error" comes from reading or writing more
>> than 2 GiB of data in a single call.
>>
>> ==rob
>>
>> --
>> Rob Latham
>> Mathematics and Computer Science Division
>> Argonne National Lab, IL USA
>>
>
>
>
> --
> Jim Edwards
>
> CESM Software Engineering Group
> National Center for Atmospheric Research
> Boulder, CO
> 303-497-1842
>
>


-- 
Jim Edwards

CESM Software Engineering Group
National Center for Atmospheric Research
Boulder, CO
303-497-1842
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/parallel-netcdf/attachments/20120808/1a57a4f6/attachment.html>