Storage#
Except in particular cases, the accounts will have the following storage scheme associated with them:
| Storage | Size | Description |
|---|---|---|
/home |
5 GB | It is recommended that you do not store data or code in this partition. When the maximum capacity is reached, you will need to move the files to /data. |
/data |
1 TB | Partition with a "soft quota " on the hired storage. For large volumes it will be necessary to request it through the support email (support@hpc.iter.es). It is accessible in /home/<user>/data. |
| /local/jobs/<username>/<jobid> | 300GB | Partition located on the node's local hard disk. This directory is automatically created when the job is executed on the node. The jobid is accessible through the $SLURM_JOBID environment variable. **The content of this partition is deleted after the execution is finished. |
Info
The idea is that users should always work from /data, leaving /home for less important files or directories, or for program configuration files. Therefore, we recommend installing virtual environments or software packages of, for example, Python or R in /data.
The /local partition is intended to improve the performance of jobs when they access storage. There are specific cases where software needs to continuously read and write to files on storage rather than in memory. In such cases, performance improvements have been seen when the access, instead of being over the network, is directly to the node's local hard disk, as it is faster. To work with this directory, in the execution script itself, the files we are going to work with must be copied to this directory, /local/jobs/<username>/<jobid>, and before finishing, also within the same script, the results must be copied back to the /data directory. This is because once the job is finished, all the contents of this directory will be deleted. If you have any questions, you can write to us at
Any changes to this storage scheme will be notified.
Backups#
User data is protected up by the backup system of the storage system. The backup scheme is as follows:
- For /home, 6 hourly copies, 2 daily copies and 2 weekly copies.
- For /data, 6 hourly copies, 2 daily copies and 2 weekly copies.
For the /local partition there are no backups because it is storage located on the hard disks of the compute nodes themselves and is intended to be used during runs and cleaned up when they are finished.
Any changes to the backup scheme will be notified.