Storage policy#

There are 3 distinct disk spaces available for each project: HOME, DATA, SCRATCH.

Each space has specific characteristics suitable to its usage which are described below. The paths to access these spaces are stocked in five variables of the shell environment: $HOME, $DATADIR, $SCRATCHDIR.

To know how much the disk spaces are occupied for your project, you can use Ligers's local commands Mybalance and myquota.

The User Directory#

$HOME : This is the home directory during an interactive connection login by SSH. This space is intended for frequently-used small-sized files such as the shell environment files, the tools, and potentially the sources and libraries if they have a reasonable size. The size of this space is limited (in space and in number of files).

The HOME characteristics are: - It is a permanent and private space. - Not suitable for high IO data transfert - Intended to receive small-sized files. - Submitted to quota per user which are intentionally rather low (10 GiB by default) and not extendable. - It is the home directory during an interactive connection. - Accessible in interactive or in a batch job via the $HOME variable :

  $ cd $HOME

The Project Directory#

$DATADIR: This is a permanent project storage space which is usable in batch. In this space, we generally store large-sized files (max 100GB per project) for use during batch executions related to the project: very large source files, libraries, data files, executable files, result files and submission scripts.

The characteristics of DATADIR are:

  • It is a permanent and shareable space to project users
  • Not suitable for high IO data transfert
  • It is partially backuped by snapshots (but a duplicated backup must be done)
  • Intended to receive large-sized files with a certain limit
  • Submitted to quotas per project (100GB and extendable on request)

  • Accessible in interactive or in a batch job via the $DATADIR variable :

    $ cd $DATADIR/

The SCRATCH Directory#

$SCRATCHDIR : This is a semi-permanent work and storage space which is usable in batch; the lifespan of the files is limited to 90 days (policy applied when global storage is 90% full). The large-sized files used during batch executions are generally stored here: the data files, result files or the computation restarts. Once the post-processing has been done to reduce the data volume, you must remember to copy the significant files into the DATADIR so that they are not lost, or transfert to outside storage as a duplicated backup.

The characteristics of the SCRATCHDIR are:

  • It is a private space and not shareable to others.
  • lifespan of the files is limited to 90 days (policy applied when global storage is 90% full) - It is not backed up.
  • It is intended to receive large-sized files.
  • It is not submitted to a quota policy (but can be applied per projet if used abusely)
  • It is accessible in interactive or in a batch job.

  • Accessible in interactive or in a batch job via the $SCRATCHDIR variable :

    $ cd $SCRATCHDIR

Summary table main disks#

Space Default capacity Features Usage
$HOME 5GB per user(*) - Home directory at connection
- Backed up space		 Storage of configuration files and small files
$DATADIR/<project_ID 100GB per project (*) - Limited backed up space - Storage of source codes and input/output data
- Execution in batch or interactive
$SCRATCHDIR No quota
900TB shared by all users
1 million inodes per user		 - GPFS Low Latency Storage (12GB/s read/write operations)
- Lifespan of unused files 90days
- Space not backed up		 - Storage of voluminous input/output data
- Execution in batch or interactive
- Optimal performance for read/write operations

(*) Space partially backed up per project