The DIFA-OPH cluster offers different storage areas with very different characteristics and limitations.

• This is a storage area available from every node. Should be used for source files, compiling code, jobs that do not need a lot of space.

• NFS-mount via Ethernet (1Gbps): not very fast but quite responsive.

• Quota limit: 50GB (soft) / 100GB (hard); check how much you're using with quota -u

• Temporary replacement for /scratch please migrate to /scratch
• Will be deleted shortly after /archive is working
• do not use for jobs' output

• This share is web-accessible (read-only) at https://apps.difa.unibo.it/files/people/Str957-cluster . Web access is read-only and it is not possible to create dynamic pages.

• Used as work area for jobs that do not need very big datasets or need to have lots of files in a single directory (not recommended, might degrade performances for all users!).

• Main archive area. To be used for large files, big datasets and archives.

  IMPORTANT: DO NOT USE FOR LOTS OF SMALL FILES!!!

  If you need some big files (say a dataset) and your code do not allow for specifying a different path, just use symlinks from $HOME to the files in /archive.

• Max size for a single file is 8TB: when archiving big dataset use splitting (preferably chunks should be less than 1TB)
• Readonly access from compute nodes, read/write only from frontends and filetransfer nodes
• Quota (both on file size and number of files): per-sector, with extra space allocated for specific projects (in /archive/projects) or bought by individuals (in /archive/extra).

• Parallel filesystem, for quick (SSD-backed) access to the data you're working on.
• No quota, but files older than TBD¹⁾ days will be automatically deleted without further notice.
• No cross-server redundancy, just local RAID: if (when) a server (or two disks in the same RAID) fails, all data becomes unavailable – always keep a copy of your important data archived elsewhere (maybe /archive, but for very important data offsite is better)

Every node does have some available space on local storage. It's useful to store temporary files that do not need to be shared between nodes. Being local, latency is very low. But local disks aren't big. $TMPDIR can usually store around 200GB of data. It gets automatically cleaned when the job terminates: if you need to keep some files, copy 'em to other storages.