Hello all,
I want to configure NIS and MPI with different network.
For example, NIS uses eth0 and MPI uses eth1 some thing like that.
How can I do that?
Axida
Okay, I fixed this today toor21219
On May 11, 2009, at 11:27 PM, Anton Starikov wrote:
Now there is another problem :)
You can try oversubscribe node. At least by 1 task.
If you hostfile and rank file limit you at N procs, you can ask
mpirun for N+1 and it wil be not rejected.
Although
I will try to prepare test-case.
--
Anton Starikov.
On May 12, 2009, at 6:57 PM, Edgar Gabriel wrote:
hm, so I am out of ideas. I created multiple variants of test-
programs which did what you basically described, and they all passed
and did not generate problems. I compiled the MUMPS libr
hm, so I am out of ideas. I created multiple variants of test-programs
which did what you basically described, and they all passed and did not
generate problems. I compiled the MUMPS library and ran the tests that
they have in the examples directory, and they all worked.
Additionally, I checke
It is usually best to separate the cluster (mpi) interfaces from the internet
interface.
Usually on a dedicated cluster it is best to have a master node that is
connected to the internet and client nodes that are connected to the master
node (and if needed tunnel the connection through it to the i
Dear all,
I am trying to install Dalton quantum chemistry program with OpenMPI over
PelicanHPC, but it ends with an error.
PelicanHPC comes with both LAM and OpenMPI preinstalled. The version of OpenMPI
is "OMPI_VERSION "1.2.7rc2"" (from version.h).
The wrappers that I use are mpif77.openmpi and
Ah... Thanks, Jeff.
If the standard would explicitly mention that MPI::ERRORS_RETURN is useless
with C++ binding, life would be a little easier...
Jacob M. Katz | jacob.k...@intel.com | Work: +972-4-865-5726 | iNet:
(8)-465-5726
-Original Message-
From:
I would say the probability is large that it is due to the recent 'fix'.
I will try to create a testcase similar to what you suggested. Could
you give us maybe some hints on which functionality of MUMPS you are
using, or even share the code/ a code fragment?
Thanks
Edgar
Jeff Squyres wrote:
Open MPI requires that each MPI process be able to connect to any
other MPI process in the same job with random TCP ports. It is
usually easiest to leave the firewall off, or setup trust
relationships between your cluster nodes.
On May 12, 2009, at 6:04 AM, feng chen wrote:
thanks a lot.
Hey Edgar --
Could this have anything to do with your recent fixes?
On May 12, 2009, at 8:30 AM, Anton Starikov wrote:
hostfile from torque PBS_NODEFILE (OMPI is compilled with torque
support)
It happens with or without rankfile.
Started with
mpirun -np 16 ./somecode
mca parameters:
btl = s
On May 12, 2009, at 9:37 AM, Jeff Squyres wrote:
2. The MPI_ERROR field in the status is specifically *not* set for
MPI_TEST and MPI_WAIT. It *is* set for the multi-test/wait
functions (e.g., MPI_TESTANY, MPI_WAITALL).
Oops! Typo -- I should have said "(e.g., MPI_TESTALL, MPI_WAITALL)".
Greetings Jacob; sorry for the slow reply.
This is pretty subtle, but I think that your test is incorrect (I
remember arguing about this a long time ago and eventually having
another OMPI developer prove me wrong! :-) ).
1. You're setting MPI_ERRORS_RETURN, which, if you're using the C++
Thank you a lot for this.
I've just checked everything again, recompiled my code as well (I'm
using SCons so it detects that the headers and the libraries changed)
and it works without a warning.
Matthieu
2009/5/12 Jeff Squyres :
> On May 12, 2009, at 8:17 AM, Matthieu Brucher wrote:
>
>> OK, th
On May 12, 2009, at 8:17 AM, Matthieu Brucher wrote:
OK, this is indeed the case. I'll try to clean the tree (I have
several other package and deleted the original 1.2.8 package) and test
again.
This misleading libltdl error message continues to bite us over and
over again (users and devel
hostfile from torque PBS_NODEFILE (OMPI is compilled with torque
support)
It happens with or without rankfile.
Started with
mpirun -np 16 ./somecode
mca parameters:
btl = self,sm,openib
mpi_maffinity_alone = 1
rmaps_base_no_oversubscribe = 1 (rmaps_base_no_oversubscribe = 0
doesn't change i
2009/5/12 Jeff Squyres :
> Or it could be that you installed 1.3.2 over 1.2.8 -- some of the 1.2.8
> components that no longer exist in the 1.3 series are still in the
> installation tree, but failed to open properly (unfortunately, libltdl gives
> an incorrect "file not found" error message if it
Or it could be that you installed 1.3.2 over 1.2.8 -- some of the
1.2.8 components that no longer exist in the 1.3 series are still in
the installation tree, but failed to open properly (unfortunately,
libltdl gives an incorrect "file not found" error message if it is
unable to load a plugi
Looking at this output, I would say that the problem is you didn't
recompile your code against 1.3.2. These are warnings about attempts
to open components that were present in 1.2.8, but no longer exist in
the 1.3.x series.
On May 12, 2009, at 2:30 AM, Matthieu Brucher wrote:
Hi,
I've m
The 1.2.x series has a bug in it when used with Torque. Simply do not
include -machinefile on your mpiexec cmd line and it should work fine.
It will automatically pickup the PBS_NODEFILE contents.
On May 12, 2009, at 1:17 AM, wrote:
Hi,
I am using OFED 1.3 version inw hich OPENMPI 1.2.
Can you send all the information listed here:
http://www.open-mpi.org/community/help/
On May 11, 2009, at 10:03 PM, Anton Starikov wrote:
By the way, this if fortran code, which uses F77 bindings.
--
Anton Starikov.
On May 12, 2009, at 3:06 AM, Anton Starikov wrote:
> Due to rankfile
thanks a lot. firewall it is.. It works with firewall's off, while that brings
another questions from me. Is there anyway we can run mpirun while firwall 's
on? If yes, how do we setup firewall or iptables?
thank you
From: Micha Feigin
To: us...@open-mpi.or
On Tue, 12 May 2009 11:54:57 +0300
Lenny Verkhovsky wrote:
> sounds like firewall problems to or from anfield04.
> Lenny,
>
> On Tue, May 12, 2009 at 8:18 AM, feng chen wrote:
>
I'm having a similar problem, not sure if it's related (gave up for the moment
on 1.3+ openmpi, 1.2.8 works fine not
sounds like firewall problems to or from anfield04.
Lenny,
On Tue, May 12, 2009 at 8:18 AM, feng chen wrote:
> hi all,
>
> First of all,i'm new to openmpi. So i don't know much about mpi setting.
> That's why i'm following manual and FAQ suggestions from the beginning.
> Everything went well un
Hi,
I've managed to use 1.3.2 (still not with LSF and InfiniPath, I start
one step after another), but I have additional warnings that didn't
show up in 1.2.8:
[host-b:09180] mca: base: component_find: unable to open
/home/brucher/lib/openmpi/mca_ras_dash_host: file not found (ignored)
[host-b:09
Hi,
I am using OFED 1.3 version inw hich OPENMPI 1.2.5 is included , I have
compiled with Intel and gcc .
Problem is that during qsub i am not able to run the jobs but same time
when i use mpiexec command it is working fine without any issue.
here is my script file ; Please help me to diagnose
Now there is another problem :)
You can try oversubscribe node. At least by 1 task.
If you hostfile and rank file limit you at N procs, you can ask mpirun
for N+1 and it wil be not rejected.
Although in reality there will be N tasks.
So, if your hostfile limit is 4, then "mpirun -np 4" and "mp
hi all,
First of all,i'm new to openmpi. So i don't know much about mpi setting. That's
why i'm following manual and FAQ suggestions from the beginning.
Everything went well untile i try to run a pllication on a remote node by using
'mpirun -np' command. It just hanging there without doing anyth
27 matches
Mail list logo
