We have a utility that checks to ensure that the shared memory backing file is
not on a shared file system. The test is checking to see if that utility can
stat and assess the nature of any file system on your node. It’s undoubtedly
stale as things have changed over the years (new file systems a
That's what I figured, but I wanted to check first. Any idea of exactly
what it's trying to check?
Prentice
On 04/26/2017 05:54 PM, r...@open-mpi.org wrote:
You can probably safely ignore it.
On Apr 26, 2017, at 2:29 PM, Prentice Bisbal wrote:
I'm trying to build OpenMPI 2.1.0 with GCC 5.4
You can probably safely ignore it.
> On Apr 26, 2017, at 2:29 PM, Prentice Bisbal wrote:
>
> I'm trying to build OpenMPI 2.1.0 with GCC 5.4.0 on CentOS 6.8. After working
> around the '-Lyes/lib' errors I reported in my previous post, opal_path_nfs
> fails during 'make check' (see below). Is t
Edgar,
Thank you for the suggestion. That fixed this problem.
Prentice
On 04/26/2017 05:25 PM, Edgar Gabriel wrote:
Can you try to just skip the --with-lustre option ? The option really
is there to provide an alternative path, if the lustre libraries are
not installed in the default directori
I'm trying to build OpenMPI 2.1.0 with GCC 5.4.0 on CentOS 6.8. After
working around the '-Lyes/lib' errors I reported in my previous post,
opal_path_nfs fails during 'make check' (see below). Is this failure
critical, or is it something I can ignore and continue with my install?
Googling only
Can you try to just skip the --with-lustre option ? The option really is
there to provide an alternative path, if the lustre libraries are not
installed in the default directories ( e.g.
--with-lustre=/opt/lustre/). There is obviously a bug that the
system did not recognize the missing arg
I'm getting the following error when I build OpenMPI 2.1.0 with GCC 5.4.0:
/bin/sh ../../../../libtool --tag=CC --mode=link gcc -O3 -DNDEBUG
-finline-functions -fno-strict-aliasing -pthread -module -avoid-version
-Lyes/lib -o libmca_fs_lustre.la fs_lustre.lo fs_lustre_component.lo
fs_lus
Everyone,
I just wanted to follow up on this, to help others, or possibly even a
future me, having problems compiling OpenMPI with the PGI compilers. I
did get it to work a few weeks ago, but I've been too busy to share my
solution here. I need to give a shout out to Matt Thompson for
provid