To be fair to all users of the cluster, please be aware of these resource limits and usage expectations.
|Name||Path||Size (GB)||Persistence||Backed up?||Purpose|
||2||Permanent||Yes||Personal storage, available on every node|
||By request||Permanent||Yes||Group storage for collaborative work|
||220,000 (shared)||2 weeks||No||Fast RAID-0 storage, generally for result files|
|Local to node||
||100||5 days||No|| Useful for large intermediate files, globally accessible from |
- Data deletion is based on modification time. You will get 3 warnings before deletion if your files or directories are expired.
- If you try to run
lson either the
/misc/cnXXdirectories, you might not see them. They are invisible because they are mounted on demand by
autofs, when an attempt is made to access a file under the directory, or using
cdto enter the directory structure.
Jobs submitted through the slurm scheduler:
|Job property||Standard Limit||Longrun Limit|
|Run time (hours)||36||72|
|Cores / CPUs||48|
|Node||Run time (minutes)||CPU limit||Memory limit|
|Login node||30||5%||5% (or 3.2 GB)|
|Compute node||10||Not allowed on compute nodes!|
- We strong discourage programs being run on the cluster without the slurm scheduler.
- Programs on the compute nodes are not allowed.
- Some programs are allowed on the login node only:
Check size of home directory
You can check your home directory quota usage with:
/usr/lpp/mmfs/bin/mmlsquota -j $(whoami) gpfs2
Block Limits | File Limits Filesystem type KB quota limit in_doubt grace | files quota limit in_doubt grace Remarks gpfs2 FILESET 6272 0 2097152 0 none | 165 0 0 0 none
Your current usage and allowed limit are highlighted in red.
Recovered deleted files
- File system snapshots are created every day and kept for 1 week.
- An additional snapshot is created every second Monday and is saved for 2 weeks.
- Users can access their home directory snapshots in:
Shared directories are available in