[petsc-dev] [OMPI users] potential bug with MPI_Win_fence() in openmpi-1.8.4

[Jeff Squyres (jsquyres)]

Per Satish's last mail (http://www.open-mpi.org/community/lists/users/2015/04/26823.php), George is looking at a followup issue...


> On Apr 30, 2015, at 2:57 PM, Ralph Castain <rhc at open-mpi.org> wrote:
> 
> Thanks! The patch wasn’t quite correct, but we have a good one now and it is going into 1.8.5 (just squeaked in before release)
> 
>> On Apr 29, 2015, at 9:50 PM, Satish Balay <balay at mcs.anl.gov> wrote:
>> 
>> OpenMPI developers,
>> 
>> We've had issues (memory errors) with OpenMPI - and code in PETSc
>> library that uses MPI_Win_fence().
>> 
>> Vagrind shows memory corruption deep inside OpenMPI function stack.
>> 
>> I'm attaching a potential patch that appears to fix this issue for us.
>> [the corresponding valgrind trace is listed in the patch header]
>> 
>> Perhaps there is a more appropriate fix for this memory corruption. Could
>> you check on this?
>> 
>> [Sorry I don't have a pure MPI test code to demonstrate this error -
>> but a PETSc test example code consistantly reproduces this issue]
>> 
>> Thanks,
>> Satish<openmpi-1.8.4.patch>_______________________________________________
>> users mailing list
>> users at open-mpi.org
>> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
>> Link to this post: http://www.open-mpi.org/community/lists/users/2015/04/26818.php
> 
> _______________________________________________
> users mailing list
> users at open-mpi.org
> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
> Link to this post: http://www.open-mpi.org/community/lists/users/2015/04/26822.php


-- 
Jeff Squyres
jsquyres at cisco.com
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/