Okay, I think I have these things fixed in r29978 on the trunk - please give it a spin and confirm so we can move it to 1.7.4


On Dec 19, 2013, at 7:54 AM, Barrett, Brian W <bwbarre@sandia.gov> wrote:

On 12/19/13 8:43 AM, "Ralph Castain" <rhc@open-mpi.org> wrote:


On Dec 19, 2013, at 6:27 AM, Barrett, Brian W <bwbarre@sandia.gov> wrote:

On 12/19/13 6:59 AM, "Jeff Squyres (jsquyres)" <jsquyres@cisco.com>
wrote:

3. Finally, we're giving a warning saying:

-----
WARNING: a request was made to bind a process. While the system
supports binding the process itself, at least one node does NOT
support binding memory to the process location.
-----

For both #1 and #3, I wonder if we shouldn't be warning if no binding
was
explicitly stated (i.e., we're just using the defaults).  Specifically,
if no binding is specified:

- if we oversubscribe, (possibly) warn about the performance loss of
oversubscription, and don't bind
- don't warn about lack of memory binding

We have a couple machines where memory binding is failing for one reason
or another.  If we're binding by default, we really shouldn't throw
error
messages about not being able to bind memory.  It's REALLY annoying.

Just to help me understand a bit better - you are saying that the node
supports process binding, but not memory binding? I don't see how the
error appears otherwise, but want to ensure I understand the code path.

That appears to be the case, yes.

Brian

--
 Brian W. Barrett
 Scalable System Software Group
 Sandia National Laboratories



_______________________________________________
devel mailing list
devel@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel