Thanks Andrew, I was getting confused with the libfabric psm provider code
inside open mpi.
2015-03-03 9:35 GMT-07:00 Friedley, Andrew :
> Hi Howard,
>
>
>
> The PSM MTL sets PSM_EP_OPEN_AFFINITY_SKIP, so if I understand right, OMPI
> already has the fix for you.
>
>
>
> Andrew
>
>
>
> *From:* d
Our PSM component always has that param set as OMPI handles affinity for it
> On Mar 3, 2015, at 8:20 AM, Howard Pritchard wrote:
>
> Hi Folks,
>
> First initial disclaimer - I've looked through the open mpi faq and have been
> unable
> so far an answer to my question below.
>
> I've been ha
Hi Howard,
The PSM MTL sets PSM_EP_OPEN_AFFINITY_SKIP, so if I understand right, OMPI
already has the fix for you.
Andrew
From: devel [mailto:devel-boun...@open-mpi.org] On Behalf Of Howard Pritchard
Sent: Tuesday, March 3, 2015 8:21 AM
To: Open MPI Developers List
Subject: [OMPI devel] psm and
Hi Folks,
First initial disclaimer - I've looked through the open mpi faq and have
been unable
so far an answer to my question below.
I've been having a discussion with one of the other trilab folks about some
issues with
using PSM within mvpaich where the default cpu affinity behavior of PSM can
Gilles --
The problem is this PR: https://github.com/open-mpi/ompi/pull/438
> On Mar 3, 2015, at 3:40 AM, Jeff Squyres (jsquyres)
> wrote:
>
> The automatic nightly tarball for a given branch is only generated on nights
> where there were commits on that branch since the last tarball was ma
* Jeff Squyres (jsquy...@cisco.com) [20150225 21:29]:
> Probably no point in re-testing the ones that already worked.
> /me wishes yet again that shell scripting had a "strict" mode that would
> /yell at you when you use "$foop" instead of "$foo" (and $foop doesn't
> /exist/was never set).
You kn
The automatic nightly tarball for a given branch is only generated on nights
where there were commits on that branch since the last tarball was made.
Results of the nightly tarball generation are sent to test...@open-mpi.org.
It looks like last night's build failed for some reason -- here's the
Folks,
the latest tarballs for both master and v1.8 were generated on Feb 28 2015.
among other things, that means the latest coverity report is from Feb 28.
is there something wrong ?
(and is someone taking care of it ?)
Cheers,
Gilles
