Data Lifecycle Policy

From HPCwiki
Revision as of 12:15, 19 June 2026 by Haars0011 (talk | contribs) (IA migration §6: new Data Lifecycle Policy (P2.13) (via create-page on MediaWiki MCP Server))
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Data on Anunna moves through a lifecycle: active working data, data you keep but no longer actively use, and data that is no longer needed. Managing that lifecycle keeps storage available and costs under control.

Active data

While you are working on it, data lives on the fast Lustre filesystem. Temporary working data on /lustre/scratch is not kept indefinitely — it may be purged automatically once the filesystem fills up (see Compute Storage and Backup Policy).

Archiving data you keep

When you are finished with data but want to keep it, move it to archival storage. Datasets there that are no longer actively used are moved to long-term tape archive automatically by the Tapeworm service, freeing the warm storage tier.

Removing data

Delete intermediate and temporary data you no longer need — it keeps the cluster usable and your costs down. Remember that backups are limited, so be sure before you delete.


See also