[slurm-users] Multinode MPI job

[Mahmood Naderan]

>srun --pack-group=0 --ntasks=2 : --pack-group=1 --ntasks=4 pw.x -i
mos2.rlx.in

Still only one node is running the processes

$ squeue
             JOBID PARTITION     NAME     USER ST       TIME  NODES
NODELIST(REASON)
             755+1    QUARTZ     myQE   ghatee  R       0:47      1 rocks7
             755+0    QUARTZ     myQE   ghatee  R       0:47      1
compute-0-2
$ rocks run host compute-0-2  "ps aux | grep pw.x"
ghatee     541  0.1  0.0 582048  7604 ?        Sl   02:29   0:00 srun
--pack-group=0 --ntasks=2 : --pack-group=1 --ntasks=4 pw.x -i mos2.rlx.in
ghatee     542  0.0  0.0  46452   748 ?        S    02:29   0:00 srun
--pack-group=0 --ntasks=2 : --pack-group=1 --ntasks=4 pw.x -i mos2.rlx.in
ghatee     559 99.6  0.1 1930560 129728 ?      Rl   02:29   0:52
/home/ghatee/QuantumEspresso621/bin/pw.x -i mos2.rlx.in
ghatee     560 99.7  0.1 1930560 129720 ?      Rl   02:29   0:52
/home/ghatee/QuantumEspresso621/bin/pw.x -i mos2.rlx.in
ghatee     590  0.0  0.0 113132  1588 ?        Ss   02:30   0:00 bash -c ps
aux | grep pw.x
ghatee     629  0.0  0.0 112668   960 ?        S    02:30   0:00 grep pw.x
$ rocks run host rocks7  "ps aux | grep pw.x"
ghatee   16219 99.0  0.1 1930484 127764 ?      Rl   10:59   1:00
/home/ghatee/QuantumEspresso621/bin/pw.x -i mos2.rlx.in
ghatee   16220 99.1  0.1 1930524 127764 ?      Rl   10:59   1:00
/home/ghatee/QuantumEspresso621/bin/pw.x -i mos2.rlx.in
ghatee   16221 99.0  0.1 1930484 127760 ?      Rl   10:59   1:00
/home/ghatee/QuantumEspresso621/bin/pw.x -i mos2.rlx.in
ghatee   16222 99.1  0.1 1930496 127760 ?      Rl   10:59   1:00
/home/ghatee/QuantumEspresso621/bin/pw.x -i mos2.rlx.in
ghatee   16391  0.0  0.0 316388 26652 pts/16   Sl+  11:00   0:00
/opt/rocks/bin/python /opt/rocks/bin/rocks run host rocks7 ps aux | grep
pw.x
ghatee   16394  0.0  0.0 113132  1368 pts/16   S+   11:00   0:00 bash -c ps
aux | grep pw.x
ghatee   16396  0.0  0.0 112664   952 pts/16   S+   11:00   0:00 grep pw.x


Regards,
Mahmood
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20190328/174e5fe1/attachment-0001.html>