[petsc-users] debugging with no X11 available

[Dominik Szczerba]

Thanks for a hint, but xterm does not seem to work with the scheduler:

xterm Xt error: Can't open display: localhost:54.0

It works, however, when invoked explicitly from the shell. I
experimented a lot with the DISPLAY variable to no avail...

It would be very helpful to be able to run 2 processes in a debugger
without relying on X11 at all...

Thanks a lot anyway,
Dominik

On Mon, Dec 12, 2011 at 2:44 PM, Aron Ahmadia <aron.ahmadia at kaust.edu.sa> wrote:
> Dear Dominik,
>
> One trick for getting around this that works on LoadLeveler (and I suspect
> SLURM) is running:
>
> xterm
>
> Instead of the usual "mpirun" when your batch script gets executed.  As long
> as the scheduler's batch script inherits your X11 environment and is running
> on the login node, you'll then have access to an xterm with full access to
> mpirun, ssh, etc...
>
> Good luck,
> Aron
>
>
> On Mon, Dec 12, 2011 at 4:35 PM, Dominik Szczerba <dominik at itis.ethz.ch>
> wrote:
>>
>> Dear all,
>>
>> Many thanks for your suggestions, but there is one fundamental
>> obstacle: there is no mpiexec available at all, everything must go
>> through a scheduler.
>>
>> I will see into what Satish proposed, i.e. to first get hold of known
>> nodes. But I am afraid this may fail, because these run some very
>> limited system.
>>
>> Regards,
>> Dominik
>>
>> On Mon, Dec 12, 2011 at 2:21 PM, Satish Balay <balay at mcs.anl.gov> wrote:
>> > On Mon, 12 Dec 2011, Matthew Knepley wrote:
>> >
>> >> On Mon, Dec 12, 2011 at 7:11 AM, Dominik Szczerba
>> >> <dominik at itis.ethz.ch>wrote:
>> >>
>> >> > Thanks for your answers. Meanwhile I clarified the situation a bit:
>> >> >
>> >> > I can bring xterm up manually from the command line, but the job is
>> >> > run using a scheduler (slurm). It then gets executed on arbitrary
>> >> > nodes (some stripped down linux) which apparently can not make X11
>> >> > connections.
>> >> >
>> >>
>> >> Sometimes you can set the env on the compute nodes, and get DISPLAY
>> >> right.
>> >
>> >
>> > With compute nodes -its not easy. Even if they have X11 installed - you
>> > might have to do multiple things:
>> >
>> > 1. allocate nodes
>> > 2. create ssh-x11 tunnels to each node thats allocated [and hope its the
>> > same localhost:10 value]
>> > 3. Now start up the parallel job with this display
>> >
>> > mpiexec -n 4 ./ex2 -start_in_debugger -display localhost:10
>> >
>> > Satish
>> >
>
>