Skip to content

Ceph

Ceph is the distributed storage engine at the foundation of CobaltCore's storage layer. It provides three storage interfaces - block (RBD), file (CephFS), and object (RGW) - from a single cluster, managed by Rook as a Kubernetes-native workload.

How CobaltCore uses Ceph

InterfaceUsed by
RBD (block)Nova/Cinder VM disks, Glance image store
CephFS (file)Shared filesystems for workloads requiring POSIX access
RGW (object)S3/Swift-compatible object storage for applications

Cluster architecture

A Ceph cluster consists of several daemon types that work together:

DaemonRole
MON (Monitor)Maintains cluster map and quorum; clients connect to MONs to locate data
MGR (Manager)Exposes metrics, hosts the dashboard, and provides orchestration APIs
OSD (Object Storage Daemon)Stores data on each disk; handles replication and recovery
MDSManages CephFS metadata; not required for RBD or RGW workloads
RGWProvides S3 and Swift HTTP APIs backed by RADOS

Data placement: CRUSH

Ceph uses the CRUSH algorithm to determine where data is stored across OSDs - no central lookup table is needed. CRUSH maps data across failure domains (hosts, racks, data centers) according to a configurable hierarchy. In CobaltCore stretched deployments, CRUSH is configured to spread replicas across two physical sites with a third tiebreaker site managed by Arbiter.

Replication and erasure coding

CobaltCore uses replication (typically 3 copies) for most pools. Erasure coding is available for large object stores where storage efficiency matters more than write latency.

See also

EU and German government funding logos

Funded by the European Union – NextGenerationEU.

The views and opinions expressed are solely those of the author(s) and do not necessarily reflect the views of the European Union or the European Commission. Neither the European Union nor the European Commission can be held responsible for them.