File system + mount point Environment Variable for Access | Purpose | Type and Size | Backup and snapshots | Intended lifetime | Cleanup strategy | Quota | Available for |
|---|---|---|---|---|---|---|---|
/home $HOME | Store source files, input data, small files Globally accessible from login and compute nodes | GPFS, 100TB | backup to tape and snapshots | Account lifetime | No cleanup | 100GB per user | All users |
/work $WORK | Collaboration space for a group Globally accessible from login and compute nodes | GPFS, 100TB | Backup upon request, at cost price. Snapshots | Group lifetime | No cleanup | 50GB* per group | All EPFL units (upon request). Not available for bachelor/master students. |
/scratch $SCRATCH | Temporary huge result files Accessible from the frontend and compute nodes within one cluster. | Fidis: Helvetios: Izar: | No backup, no snapshots | 2 weeks | Automatic deletion of files and empty directories older than two weeks may happen without notice | Quotas may be in place to prevent runaway tasks filling the filesystem. A typical limit would be 1/3 or 1/2 of the total space. | All users |
/tmp/${SLURM_JOB_ID} $TMPDIR | Temporary, local file space for jobs on compute nodes. Not available on login nodes. | local (node), between 64 and 512 GB | No backup, no snapshots | Job execution | Content is deleted after job end | no | All users |
* Space on work is charged for and, as such, the quota of the group depends on the amount of space purchased. There is no backup by default but a laboratory may request such a service. The price for backup will be the cost price to SCITAS.
The price for work is per TB/year, usually sold for 3 years, and can be found in our website:
https://www.epfl.ch/research/facilities/scitas/getting-started/prospective-users-howto/
Each group can have 50GB for free.
The contents of the home file-system are backed-up on a daily basis with a six month retention period. The backed up data are held at a separate physical location to the original data.
The contents of the work file-system are not backed up by default
The scratch file-systems are not backed-up under any circumstances.
The scratch file-systems are only for short-lived files and, in the case of insufficient free space, files older than two weeks may be deleted without notice in order to ensure the usability of the cluster.
When a scratch filesystem reaches a certain level of use (normally 90%) an automatic cleanup procedure is activated. Starting with the oldest files present deletion takes place until the occupancy has been reduced to 70%. Only files less than 2 weeks old are sure not to be deleted by the cleanup mechanism.
When a user no longer has a valid account on the clusters any files belonging to him on home are removed from the servers. They will remain on backup for 6 months after the user has left EPFL. The head of the laboratory is responsible for ensuring that these data are correctly managed. He or she can ask for a retrieval from backup.
The work file-system is divided by laboratory and, as directories of users who leave EPFL cannot be deleted by their colleagues, an intervention is required.
Once a user is no longer accredited, files belonging to them in scratch can be deleted without notice.
A snapshot is the state of a system at a particular point in time. On our clusters, the home and work filesystems are snapshotted daily and snapshots are kept for one week. This is particularly useful in case a user removes a file by mistake.
Daily snapshots of the home and work filesystems can be found in /home/.snapshots, /work/.snapshots, respectively.