Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
slurm [2020/05/19 02:03] mickey [Trabajando con SLURM] |
slurm [2020/09/17 13:19] (current) admin [Trabajando con SLURM] |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | ====== SLURM ====== | + | ====== SLURM 19.04 ====== |
| Conceptos básicos | Conceptos básicos | ||
| Line 20: | Line 20: | ||
| **Simple usage for soroban** | **Simple usage for soroban** | ||
| - | 0. Note. | ||
| - | '-p intel' (--partition=intel) is required for soroban. | ||
| - | 1. Save below as text file (e.g. my_first_slurm.sh). | + | 0. Note. |
| + | |||
| + | '-p intel' (equivalent long option: '–partition=intel') is required for soroban. | ||
| + | |||
| + | 1. Save below as text file (e.g. my_first_slurm.sh). | ||
| <code> | <code> | ||
| #!/bin/bash | #!/bin/bash | ||
| #SBATCH --job-name=example # Nombre para el trabajo a ejecutar en el cluster | #SBATCH --job-name=example # Nombre para el trabajo a ejecutar en el cluster | ||
| #SBATCH --partition=intel | #SBATCH --partition=intel | ||
| - | #SBATCH -n 32 # Debe de ser un número múltiplo de 16 | ||
| - | #SBATCH --ntasks-per-node=16 # máximo por blade | ||
| #SBATCH --output=example_%j.out | #SBATCH --output=example_%j.out | ||
| #SBATCH --error=example_%j.err | #SBATCH --error=example_%j.err | ||
| Line 37: | Line 38: | ||
| </code> | </code> | ||
| - | 2. Submit it as SLURM job. | + | 2. Submit it as SLURM job. |
| - | sbatch <filename> (e.g. sbatch my_first_slurm.sh) | + | |
| + | sbatch (e.g. sbatch my_first_slurm.sh) | ||
| + | |||
| + | 3. Check progress. | ||
| - | 3. Check progress. | ||
| squeue | squeue | ||
| Line 47: | Line 50: | ||
| #!/bin/bash | #!/bin/bash | ||
| #SBATCH --job-name=example # Nombre para el trabajo a ejecutar en el cluster | #SBATCH --job-name=example # Nombre para el trabajo a ejecutar en el cluster | ||
| - | #SBATCH --partition=troquil | + | #SBATCH --partition=intel |
| - | #SBATCH -n 32 # Debe de ser un número múltiplo de 16 | + | #SBATCH -n 32 # Debe de ser un número múltiplo de 16, número de procesos |
| - | #SBATCH --ntasks-per-node=16 # máximo por blade | + | #SBATCH --ntasks-per-node=16 # máximo por nodo |
| #SBATCH --output=example_%j.out | #SBATCH --output=example_%j.out | ||
| #SBATCH --error=example_%j.err | #SBATCH --error=example_%j.err | ||
| - | #SBATCH --mail-user=username@ufrontera.cl | + | #SBATCH --mail-user=username@ufrontera.cl #correo para notificacion |
| #SBATCH --mail-type=ALL | #SBATCH --mail-type=ALL | ||
| Line 58: | Line 61: | ||
| </code> | </code> | ||
| + | |||
| + | ===== 4. Ejemplo básico 3 ===== | ||
| + | |||
| + | Este es un ejemplo de un script (ejemplo3.sh) con los elementos minimos para ejecutar el programa R-3.6.1 a través de slurm: | ||
| + | |||
| + | <code> | ||
| + | #!/bin/bash | ||
| + | |||
| + | #SBATCH -J R-NOMBRE-SIMULACION | ||
| + | #SBATCH -a 1-11%3 | ||
| + | #SBATCH --nodes=1 | ||
| + | #SBATCH --tasks-per-node=1 | ||
| + | #SBATCH --mem=100G | ||
| + | #SBATCH --partition=intel | ||
| + | |||
| + | module load R/3.6.1 | ||
| + | |||
| + | cmds=( | ||
| + | 'sleep 10;echo 10' | ||
| + | 'sleep 20;echo 20' | ||
| + | 'sleep 30;echo 30' | ||
| + | 'sleep 40;echo 40' | ||
| + | 'sleep 50;echo 50' | ||
| + | ) | ||
| + | eval ${cmds[$SLURM_ARRAY_TASK_ID - 1]} | ||
| + | </code> | ||
| + | |||
| + | Para enviar este script a slurm, crear un job, y comenzar el procesamiento se requiere lo siguiente: | ||
| + | |||
| + | <code> | ||
| + | chmod +x ejemplo3.sh | ||
| + | </code> | ||
| + | |||
| + | <code> | ||
| + | sbatch ejemplo3.sh | ||
| + | </code> | ||
| ===== List of available clusters and partitions ===== | ===== List of available clusters and partitions ===== | ||
| Line 84: | Line 123: | ||
| * scancel | * scancel | ||
| * scontrol | * scontrol | ||
| + | * sinfo | ||
| * squeue | * squeue | ||
| * sreport | * sreport | ||