Well, in this case, hostname is running at the right time. However I'm
not getting multiple output files with the %N template like the docs say
I will:
balter@exahead1:~/slurm_tutorial$ cat proc.sub
#!/bin/bash
#SBATCH --job-name=proc
#SBATCH --nodes=4
#SBATCH --ntasks=4
#SBATCH --tasks-per-node=1
#SBATCH --output="proc_%n_%N_%j.out"
#SBATCH --error="proc_%n_%N_%j.err"
names=(
"paul mccartney"
"john lennon"
"george harrison"
"ringo starr"
)
#srun hostname
srun printenv SLURM_PROCID
srun hostname
#srun hello_to.sh ${names[$SLURM_PROCID]}
#srun hello_names.sh
balter@exahead1:~/slurm_tutorial$ sbatch proc.sub
Submitted batch job 503
balter@exahead1:~/slurm_tutorial$ for i in *.out; do echo "*** $i ***";
cat $i; done
*** proc_0_exanode-2-8_503.out ***
0
1
2
3
exanode-2-8
exanode-4-44
exanode-4-12
exanode-6-0
On 6/14/17 2:17 PM, TO_Webmaster wrote:
I guess $(hostname) is evaluated too early (on the batch host). Please
check the output of "srun hostname".
2017-06-14 21:23 GMT+02:00 Ariel Balter <[email protected]>:
I want to create an array of jobs, but have them execute on different nodes.
This is what I'm trying:
```
balter@exahead1:~/slurm_tutorial$ cat nodes.sub
#!/bin/bash
#SBATCH --job-name=nodes
#SBATCH --array=0-3
#SBATCH --nodes=4
#SBATCH --tasks-per-node=1
##SBATCH --ntasks=4
#SBATCH --output="hello_%N_%A_%a_%j.out"
#SBATCH --error="hello_%N_%A_%a_%j.err"
srun echo "SLURM_JOB_NAME: $SLURM_JOB_NAME SLURM_JOB_ID: $SLURM_JOB_ID
SLURM_ARRAY_TASK_ID: $SLURM_ARRAY_TASK_ID SLURM_ARRAY_JOB_ID:
$SLURM_ARRAY_JOB_ID SLURM_PROCID: $SLURM_PROCID hostname: $(hostname)"
balter@exahead1:~/slurm_tutorial$ sbatch nodes.sub
balter@exahead1:~/slurm_tutorial$ for i in *.out; do echo "*** $i ***"; cat
$i; done
*** hello_exanode-6-3_408_0_409.out ***
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 409 SLURM_ARRAY_TASK_ID: 0
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 409 SLURM_ARRAY_TASK_ID: 0
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 409 SLURM_ARRAY_TASK_ID: 0
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 409 SLURM_ARRAY_TASK_ID: 0
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
*** hello_exanode-6-3_408_1_410.out ***
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 410 SLURM_ARRAY_TASK_ID: 1
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 410 SLURM_ARRAY_TASK_ID: 1
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 410 SLURM_ARRAY_TASK_ID: 1
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 410 SLURM_ARRAY_TASK_ID: 1
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
*** hello_exanode-6-3_408_2_411.out ***
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 411 SLURM_ARRAY_TASK_ID: 2
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 411 SLURM_ARRAY_TASK_ID: 2
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 411 SLURM_ARRAY_TASK_ID: 2
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 411 SLURM_ARRAY_TASK_ID: 2
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
*** hello_exanode-6-3_408_3_408.out ***
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 408 SLURM_ARRAY_TASK_ID: 3
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 408 SLURM_ARRAY_TASK_ID: 3
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 408 SLURM_ARRAY_TASK_ID: 3
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
SLURM_JOB_NAME: nodes SLURM_JOB_ID: 408 SLURM_ARRAY_TASK_ID: 3
SLURM_ARRAY_JOB_ID: 408 SLURM_PROCID: 0 hostname: exanode-6-3
```
--
Ariel Balter
"Don't believe everything you think."
509-713-0087
☮
