Environment variable option to disable mpibind
- Dominant language
- C
- Stars
- 53
- Forks
- 11
- Avg merge
- 1h
- Merged PRs (30d)
- 3
Description
In the case of Flux, we don't want Flux processes to be bound by mpibind when launched under Slurm. Instead, we only want mpibind to be activated once Flux has started. [In parts of Flux's documentation](https://flux-framework.readthedocs.io/en/latest/batch.html#launching-flux-in-slurm-s-batch-mode), we currently recommend users launch Flux under Slurm with `srun --mpibind=off flux start`, but this only applies to LLNL clusters ([open issue](https://github.com/flux-framework/flux-docs/issues/99)).
An alternate solution would be to suggest users to do `MPIBIND=off srun flux start` or set `MPIBIND=off` in an lmod file, but this requires mpibind to support providing options via environment variables. Once Flux is started, we could unset the `MPIBIND` env var when launching jobs (and reactivating mpibind via the Flux mpibind job shell plugin is also an option).
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are named. Start by tracing mpibind's option parsing and launch path, then determine how an MPIBIND=off setting should affect activation under Slurm and later Flux launches. Done means the environment-variable behavior is implemented and covered by relevant tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- c
- Domain
- hpc
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100