Addressing a billion-entries multi-petabyte distributed file system backup problem with cback: from files to objects

CERNBox is the cloud collaboration hub at CERN. The service has more than 37,000 user accounts. backup of and project spaces data critical for service. underlying storage system hosts over a billion files which amount to 12PB distributed thousands disks with tworeplica layout. Performing operation this vast number non-trivial task. original (an in-house event-driven file-level system) been reconsidered replaced by new scalable infrastructure based on open source tool RESTIC. system, codenamed cback , provides features needed in HEP community guarantee safety smooth from administrators. Daily snapshot-based backups all our areas along automatic verification restores are possible development. also de-duplicated blocks stored as objects disk-based S3 cluster another geographical location CERN campus, reducing costs protecting major catastrophic events. We report design operational experience running future improvement possibilities.