Did you run with a higher number of procs?

-jms
Sent from my PDA

 -----Original Message-----
From:   Richard Graham [mailto:rlgraham@ornl.gov]
Sent:   Friday, November 02, 2007 04:05 PM Eastern Standard Time
To:     Open MPI Developers
Subject:        Re: [OMPI devel] openib currently broken

It does.  I was able to run the point-to-point intel tests with 3 procs
using sm and self, ob1 and dr.

Rich


On 11/2/07 3:57 PM, "Don Kerr" <Don.Kerr@sun.com> wrote:

> Rich,
>
> Do the ompi_free_list changes impact the sm btl?   Solaris SPARC sm btl
> seems to have an issue starting with last nights put back but I have not
> looked into it yet.
>
> -DON
>
> Richard Graham wrote:
>
>> R16641 should have fixed the regression.  Anyone using
>> ompi_free_list_t_ex() and providing
>>  a memory allocator would have been bitten by this, since I did not
>> update this function
>>  (which will be deprecated in favor of a version parallel to
>> ompi_free_list_t_new) to initialize
>>  the new fields defined.  From looking through the btls, this seems to
>> be only the openib btl.
>>
>> Rich
>>
>>
>> On 11/2/07 12:31 PM, "Richard Graham" <rlgraham@ornl.gov> wrote:
>>
>>
>>
>>
>>     On 11/2/07 12:21 PM, "Jeff Squyres" <jsquyres@cisco.com> wrote:
>>
>>         The freelist changes from yesterday appear to have broken the
>>         openib
>>         btl.  We didn't get lots of test failures in MTT last night only
>>         because there was a separate (unrelated) typo in the ofud BTL
>>         that 
>>         prevented the nightly tarball from building on any IB-capable
>>         machines.  :-)
>>
>>         Rich hopes to look into fixing the openib BTL problem today; he
>>         thinks it's a case of a simple oversight: the openib BTL is
>>         not using
>>         the new freelist init functions.
>>
>>         Rich: are there other places that are not using the new init
>>         functions that need to?
>>
>>>> the ompi free list has two init functions, I changed just
>>         one.  The IB btl uses the
>>>> one I have not yet changed, but the pml uses the one I did
>>         change.
>>
>>>> rich
>>
>>         --
>>         Jeff Squyres
>>         Cisco Systems
>>
>>         _______________________________________________
>>         devel mailing list
>>         devel@open-mpi.org
>>         http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>>
>>
>>     ------------------------------------------------------------------------
>>     _______________________________________________
>>     devel mailing list
>>     devel@open-mpi.org
>>     http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>>
>> ------------------------------------------------------------------------
>>
>> _______________________________________________
>> devel mailing list
>> devel@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>> 
>>
> _______________________________________________
> devel mailing list
> devel@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel

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