Running Interactive Parallel Batch Jobs on Triton

In order to run interactive parallel batch jobs on Triton, use the command:

which will provide a login to the launch node as well as the PBS_NODEFILE file with all nodes assigned to the interactive job.

Other qsub options can be used, such as those described by the
man qsub command.

As with any job, the interactive job will wait in the queue until the specified number of nodes become available. Requesting fewer nodes and shorter wall clock times may reduce the wait time because the job can more easily backfill among larger jobs.

The showbf command gives information on available time slots:

Partition     Tasks  Nodes      Duration   StartOffset       StartDate
---------     -----  -----  ------------  ------------  --------------
ALL               8      8      INFINITY      00:00:00  13:45:30_04/03

This command will provide an accurate prediction of when the submitted job will be allowed to run.

The exit command will end the interactive job.

To run an interactive job with a wall clock limit of 30 minutes, using two nodes and two processors per node:

$ qsub -I -V -l walltime=00:30:00,nodes=2:ppn=2
qsub: waiting for job 75.triton-42.sdsc.edu to start
qsub: job 75.triton-42.sdsc.edu ready

$ echo $PBS_NODEFILE
/opt/torque/aux/75.triton-42.sdsc.edu

$ more /opt/torque/aux/75.triton-42.sdsc.edu
tcc-2-31
tcc-2-31
tcc-2-25
tcc-2-25

$ mpirun -machinefile /opt/torque/aux/75.triton-42.sdsc.edu -np 4 hostname
tcc-2-25.local
tcc-2-25.local
tcc-2-31.local
tcc-2-31.local