Another dumb/obvious question, but have you tried to submit a sample compiled application across multiple nodes? I once did this and it was forever stuck in
a wait state. The reasoning behind this was the admin did not clear my account to use multiple nodes. Once he realized the job had been stuck that way for over a month, he corrected it.
There are video tutorials available online, I think. I personally found a Power Point presentation which went step by step. The problem is Eclipse and the plugin
changes so often, those tutorials can be a bit hard to follow because many things may have been changed, especially in the menus where they tell you to find things.
From: devendra rai [mailto:rai.devendra@yahoo.co.uk]
Sent: Tuesday, October 25, 2011 5:29 AM
To: Meredith Creekmore; Open MPI Users
Subject: Re: [OMPI users] Visual debugging on the cluster
Yes, I have tried the plugin already. The problem is that the plugin seems to be forever stuck in "Waiting for job information" stage. I scouted
around a bit on how to solve the problem, and it did not seem straightforward. At least, the solution to me seemed like a one-time wonder.
And, this is how I shifted to parallel visual debuggers, using other tools like kdbg.
However, in case you have PTP plugin working for you on Linux, it would help a lot if you can send screenshots/notes on how to set it up for multiple
machines.
So, summing up, I am still clueless.
Thanks for your time though.
From: Meredith Creekmore
<mtcreekmore@broncs.utpa.edu>
To: devendra rai <rai.devendra@yahoo.co.uk>; Open MPI Users <users@open-mpi.org>
Sent: Monday, 24 October 2011, 22:31
Subject: RE: [OMPI users] Visual debugging on the cluster
Not a direct answer to your question, but have you tried using Eclipse with the Parallel Platform Tools installed?
From: users-bounces@open-mpi.org [mailto:users-bounces@open-mpi.org]
On Behalf Of devendra rai
Sent: Monday, October 24, 2011 2:50 PM
To: users@open-mpi.org
Subject: [OMPI users] Visual debugging on the cluster
I have been struggling with visual debugging on cluster machines. So far, I tried to work around the problem, or total avoid it, but no more.
I have three machines on the cluster: a.s1.s2, b.s1.s2 and c.s1.s2. I do not have admin privileges on any of these machines.
Now, I want to run a visual debugger on all of these machines, and have the windows come up.
13. Can I run GUI applications with Open MPI?
Yes, but it will depend on your local setup and may require additional setup.
In short: you will need to have X forwarding enabled from the remote processes to the display where you want output to appear. In a secure environment, you can simply
allow all X requests to be shown on the target display and set the DISPLAY environment variable in all MPI process' environments
to the target display, perhaps something like this:
|
shell$ hostname
shell$ xhost +
|
However, this technique is not generally suitable for unsecure environments (because it allows anyone to read and write to your display). A slightly more secure way is
to only allow X connections from the nodes where your application will be running:
|
shell$ hostname
shell$ xhost +compute1 +compute2 +compute3 +compute4
compute1 being added to access control list
compute2 being added to access control list
compute3 being added to access control list
compute4 being added to access control list
|
(assuming that the four nodes you are running on are
compute1 through
compute4).
Other methods are available, but they involve sophisticated X forwarding through mpirun and are generally more complicated than desirable.
This still gives me "Error: Can't open display:" problem.
My mpirun shell script contains:
mpirun-1.4.3 -hostfile hostfile -np 3 -v -nooversubscribe --rankfile rankfile.txt --report-bindings -timestamp-output ./testdisplay-window.sh
where rankfile and hostfile contain a.s1.s2, b.s1.s2 and c.s1.s2, and are proper.
The file ./testdisplay-window.sh:
#!/bin/bash
echo "Running xeyes on `hostname`"
DISPLAY=a.s1.s2:11.0
xeyes
exit 0
I see that my xauth list output already contains entries like:
a.s1.s2/unix:12 MIT-MAGIC-COOKIE-1 aa16a9573f42224d760c7bb618b48a6f
a.s1.s2/unix:10 MIT-MAGIC-COOKIE-1 0fb6fe3c2e35676136c8642412fb5809
a.s1.s2/unix:11 MIT-MAGIC-COOKIE-1 a3a65970b5f545bc750e3520a4e3b872
I seem to have run out of ideas now.
However, this works prefectly on any of the machines a.s1.s2,
b.s1.s2 or
c.s1.s2:
(for example, running from a.s1.s2):
ssh b.s1.s2 xeyes
Can someone help?
Best
Devendra Rai