[mpich-discuss] Facing problem while using MPI_File_set_view

[Christina Patrick]

Thank you very much. Since the API MPI_Type_create_subarray() is very
easy to use as compared to other API's used to create data types in
MPI, I would really appreciate a solution to this problem.
FYI: I am using pvfs 2.8.0.
I will check it out with pvfs2.8.1 and keep you posted.

Regards,
Christina.

On Wed, May 27, 2009 at 5:29 PM, Rob Latham <robl at mcs.anl.gov> wrote:
> On Wed, May 27, 2009 at 05:15:22PM -0400, Christina Patrick wrote:
>> One reason why I feel that this is a bug in the MPI code is that even
>> if I reduce the array size to 16 x 16 (type double) ~ 2048 bytes and
>> specify a COLL_BUFSIZE of (32*8) ~ 256 bytes, I get this error. (If I
>> specify the COLL_BUFSIZE to be (16*4*8) ~ 512 bytes, (the size of the
>> entire row view), the error disappears.
>>
>> I will appreciate your inputs and suggestions and help.
>
> Hi.  This might be a bug in ad_pvfs, but it actually looks more like a
> bug in PVFS itself.  Furthermore, I think we might have fixed this in
> CVS as I cannot reproduce this when I checkout PVFS from CVS, but do get
> a crash similar to yours when I use pvfs-2.8.1 .
>
> Yesterday I was working with the SVN version of MPICH2 and the CVS
> version of PVFS. perhaps that is why I could not reproduce the failure
> you were seeing.
>
> ==rob
>
> --
> Rob Latham
> Mathematics and Computer Science Division
> Argonne National Lab, IL USA
>