add slurm real time debugging

label: "Utilisation HPC"

label: "HPC guide"

icon: ":computer:"

---

order: 1

---

# SLURM guide

## Debug in Real-time on SLURM

### Problem

Debugging a code by submitting jobs to a supercomputer is an inefficient

process. It goes something like this :

1. Submit job and wait in queue.

1. Check for errors/change code.

1. Repeat endlessly until your code works.

### Solution

Fortunately, there’s a better way, you can debug in real-time like so:

1. Request a debugging or interactive node and wait in queue :

   ```sh

   srun --partition=<name> --nodes=<nnodes> --gres=gpu:<ngpus> --time=<time> --pty bash -i

   ```

1. This is how it looks once the interactive job starts :

   ```sh

   srun: job 12345 queued and waiting for resources

   srun: job 12345 has been allocated resources

   ```

1. Check for errors/change code continuously until code is fixed or node has

   timed out.

### Sources

- [HPC-UiT Services User Documentation](https://hpc-uit.readthedocs.io/en/latest/jobs/interactive.html#starting-an-interactive-job)

---

label: "Slurm"

---