Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] Update on 1.7.5
From: Paul Hargrove (phhargrove_at_[hidden])
Date: 2014-02-09 14:39:05


Testing v1.7 w/ oshmem I did have a few problems:
  http://www.open-mpi.org/community/lists/devel/2014/02/14056.php
  http://www.open-mpi.org/community/lists/devel/2014/02/14057.php
  http://www.open-mpi.org/community/lists/devel/2014/02/14059.php
  Solaris MPI_Init failures that I have yet to triage
However, only the second of these four is oshmem related.

It is worth mentioning that I did have success building on 44 distinct
(os,compiler,abi) combinations.

-Paul

On Sat, Feb 8, 2014 at 10:09 AM, Ralph Castain <rhc_at_[hidden]> wrote:

> The OSHMEM update is now in the 1.7.5 tarball - I would appreciate it if
> people could exercise the tarball to ensure nothing broke. Note that shmem
> examples are executing, but shmemrun is hanging instead of exiting.
> Mellanox is looking into the problem.
>
> For now, I just want to verify that MPI operations remain stable.
>
> Thanks
> Ralph
>
> On Feb 7, 2014, at 2:09 PM, Paul Hargrove <phhargrove_at_[hidden]> wrote:
>
> Ralph,
>
> I'll try to test tonight's v1.7 taball for:
> + ia64 atomics (#4174)
> + bad getpwuid (#4164)
> + opalpath_nfs/EPERM (#4125)
> + torque smp (#4227)
>
> All but torque are fully-automated tests and I need only check my email
> for the results.
> The torque one will require manual job submission.
>
> -Paul
>
>
> On Fri, Feb 7, 2014 at 1:55 PM, Ralph Castain <rhc_at_[hidden]> wrote:
>
>> Hi folks
>>
>> As you may have noticed, I've been working my way thru the CMR backlog on
>> 1.7.5. A large percentage of them were minor fixes (valgrind warning
>> suppressions, error message typos, etc.), so those went in the first round.
>> Today's round contains more "meaty" things, but I still consider them
>> fairly low risk as the code coverage impacted is contained.
>>
>> I'm going to let this run thru tonight's MTT - if things look okay
>> tomorrow, I will roll the OSHMEM cmr into 1.7.5 over the weekend. This is
>> quite likely to destabilize the branch, so I expect to see breakage in the
>> resulting MTT reports. We'll deal with it as we go.
>>
>> Beyond that, there are still about a dozen CMRs in the system awaiting
>> review. Jeff has the majority, followed by Nathan. If folks could please
>> review them early next week, I would appreciate it.
>>
>> Thanks
>> Ralph
>>
>> _______________________________________________
>> devel mailing list
>> devel_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>
>
>
> --
> Paul H. Hargrove PHHargrove_at_[hidden]
> Future Technologies Group
> Computer and Data Sciences Department Tel: +1-510-495-2352
> Lawrence Berkeley National Laboratory Fax: +1-510-486-6900
> _______________________________________________
> devel mailing list
> devel_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>
>
>
> _______________________________________________
> devel mailing list
> devel_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>

-- 
Paul H. Hargrove                          PHHargrove_at_[hidden]
Future Technologies Group
Computer and Data Sciences Department     Tel: +1-510-495-2352
Lawrence Berkeley National Laboratory     Fax: +1-510-486-6900