I've seen several suggestions for "home-brew" systems, usually modifying
the paging mechanism. However there is one commercial solution I have
seen advertised: https://numascale.com/index.html
I've never used them and have no idea if they are any good or as good as
they claim, you'll have to d
That looks like a login issue to compute-02-02, -00 and -03. Can you
ssh to them?
From: users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] On
Behalf Of Syed Ahsan Ali
Sent: 01 August 2012 08:45
To: Open MPI Users
Subject: [OMPI users] Permission denied, please try again.
Dear
SuSE supports an application mpi-selector which installs when you load
the (broken) SuSE version of OpenMPI. According to your choice of mpi
implementation it will correctly set PATH, MANPATH and LD_LIBRARY_PATH
for you.
The initial installation drops the usual pair (.sh, .csh) of scripts
into /e
cember 2011 16:37
To: Open MPI Users
Subject: Re: [OMPI users] UC UC Clean install fails
We don't really have any contacts at SUSE. Can you query to fid out who
te upstream provider is and send them a note that their OMPI package is
broken?
Sent from my phone. No type good.
On Dec 21, 2011, at
a tarball and installing by hand.
On Dec 21, 2011, at 8:13 AM, Rushton Martin wrote:
> I agree it looks like it, but YaST ought to be able to work out
> dependencies. Anyhow, here is the listing:
>
> isis:/usr/lib64/mpi/gcc/openmpi # ls -R lib64
> lib64:
> libmca_common
/lib64
On Dec 21, 2011, at 6:26 AM, Rushton Martin wrote:
> For run-time problems:
>
> 1.Check the FAQ first.DONE. nothing
obvious.
> 2.The version of Open MPI that you're using. openmpi-1.4.3
> 3.The config.log file Ins
ecember 2011 12:51
To: Open MPI Users
Cc: Open MPI Users
Subject: Re: [OMPI users] Clean install fails
Your OMPI install looks busted. Can you send all the info listed in the
"support" section on the OMPI web site?
Sent from my phone. No type good.
On Dec 21, 2011, at 7:37 AM, "R
I've just completed installing OpenSuSE 12.1 on a standalone node.
Using the bundled GCC and OpenMPI the user code fails. I've reduced the
problem to that below, but without the source I'm not sure what
orte_init is after. Using mpirun -np 1 or -np 2 both fail in the same
way. Any suggestions?
There appears to be some confusion about ramdisks and tmpfs. A ramdisk
sets aside a fixed amount of memory for its exclusive use, so that a
file being written to ramdisk goes first to the cache, then to ramdisk,
and may exist in both for some time. tmpfs however opens up the cache
to programs so
OMPI -- are you using QLogic IB NICs? That's the
only thing named "PSM" in Open MPI.
On Apr 14, 2011, at 9:46 AM, Rushton Martin wrote:
> A typical file is called
> /dev/shm/psm_shm.41e04667-f3ba-e503-8464-db6c209b3430
>
> I had assumed that these were from OMPI, but
nking
On Apr 14, 2011, at 9:22 AM, Rushton Martin wrote:
> For your information: we were supplied with a script when we bought
> the cluster, but the original script made the assumption that all
> processes and shm files belonging to a specific user ought to be
> deleted. This is a
Thanks for the response. In the last 5 minutes I have managed to get
some output from the prologue.parallel scripts, it turns out that the
Torque Administrator's Manual was wrong, and I was fool enough to
believe it! Now that I've got a working model I can start to sort out
the mess with psm_shm
I notice from the developer archives that there was some discussion
about when psm_shm... files ought to be unlinked from /dev/shm:
-
Subject: Re: [OMPI devel] System V Shared Memory for Open MPI: Request
forCommunity Input and Testing
From: Barrett, Brian W (bwbarr
it did allow us to run jobs reliably to completion when
the code involved such issues.
On Apr 13, 2011, at 10:07 AM, Rushton Martin wrote:
> The 16 cores refers to x3755-m2s. We have a mix of 3550s and 3755s in
> the cluster.
>
> It could be memory, but I think not. The jobs are well
printing this email.
-Original Message-
From: users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] On
Behalf Of Reuti
Sent: 13 April 2011 16:53
To: Open MPI Users
Subject: Re: [OMPI users] Over committing?
Am 13.04.2011 um 17:09 schrieb Rushton Martin:
> Version 1.3.2
>
> C
emory is static, indeed
most of the memory is configured as a humungous one-dimensional array.
Very old school but what the heck, it works well when it's not hung.
-Original Message-
From: users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] On
Behalf Of Rushton Martin
Sent
n Apr 13, 2011, at 9:09 AM, Rushton Martin wrote:
> Version 1.3.2
>
> Consider a job that will run with 28 processes. The user submits it
> with:
>
> $ qsub -l nodes=4:ppn=7 ...
>
> which reserves 7 cores on (in this case) each of x3550x014 x3550x015
> and
ain
Sent: 13 April 2011 15:34
To: Open MPI Users
Subject: Re: [OMPI users] Over committing?
On Apr 13, 2011, at 8:13 AM, Rushton Martin wrote:
> The bulk of our compute nodes are 8 cores (twin 4-core IBM x3550-m2).
> Jobs are submitted by Torque/MOAB. When run with up to np=8 there is
The bulk of our compute nodes are 8 cores (twin 4-core IBM x3550-m2).
Jobs are submitted by Torque/MOAB. When run with up to np=8 there is
good performance. Attempting to run with more processors brings
problems, specifically if any one node of a group of nodes has all 8
cores in use the job hang
19 matches
Mail list logo
