btlapply submitting to only a small number of nodes in Slurm

Open
#265 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
20/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
hpc, r
Domain
distributed-systems, infrastructure

Research direction

Start by reproducing the btlapply submission on the reported 16-node Slurm cluster and compare its allocation with srun -N 16 hostname. Determine whether the node limit comes from batchtools usage or Slurm configuration; done means identifying a reproducible cause and documenting the fix.

Written by the indexing model from the issue text.

Description

Hi,

I have a recurring problem with btlapply, whichever code I use inside. I'm not sure if it's a bug in batchtools, a problem in the way I use it or an error in my Slurm configuration.
I have 16 nodes, each with 40 CPUs. Whatever I submit using btlapply, it never uses more than 1 or 2 nodes. And even the second node is used half.
sinfo reports all the other nodes in idle state.
srun -N 16 hostname will correctly print the hostname of each node, meaning I can send jobs to all the nodes.

Any idea or suggestions on how to fix this problem or where to look at?

Dominant language
R
Stars
184
Forks
53
Avg merge
7d 2h
Merged PRs (30d)
1

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from mlr-org/batchtools

All issues in mlr-org/batchtools

Similar issues

More R issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.