Skip to content

Commit

Permalink
ATP module known issue and fix
Browse files Browse the repository at this point in the history
  • Loading branch information
RuiApostolo committed Apr 29, 2024
1 parent 226be96 commit 023ee07
Show file tree
Hide file tree
Showing 2 changed files with 13 additions and 0 deletions.
11 changes: 11 additions & 0 deletions docs/known-issues/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,17 @@ active investigation by HPE Cray and the wider service.

## Open Issues

### ATP Module tries to write to /home from compute nodes (Added: 2024-04-29)

The ATP Module tries to execute a `mkdir` command in the `/home` filesystem.
When running the ATP module on the compute nodes, this will lead to an error, as the compute nodes cannot access the `/home` filesystem.

To circumvent the error, add the line:

export HOME=${HOME/home/work}

in the slurm script, so that the ATP module will write to `/work` instead.

### When close to storage quota, jobs may slow down or produce corrupted files (Added: 2024-02-27)

For situations where users are close to user or project quotas on work (Lustre) file systems we have
Expand Down
2 changes: 2 additions & 0 deletions docs/user-guide/debug.md
Original file line number Diff line number Diff line change
Expand Up @@ -496,6 +496,8 @@ environment variable to 1 on the login node:

module load atp
export ATP_ENABLED=1
# Fix for a known issue:
export HOME=${HOME/home/work}

Then, launch your job using `srun` as a background task (by adding an
`&` at the end of the command). For example, if you are running an
Expand Down

0 comments on commit 023ee07

Please sign in to comment.