Object Storage
S3-compatible storage on Ceph
Block Storage
Block storage that shrugs off failures.
We build highly available block storage on Ceph RBD, replicated across separate failure domains. Attached natively, over NVMe/TCP or iSCSI, for hypervisors, Kubernetes and bare metal.
- Ceph RBD
- NVMe/TCP
- iSCSI
- ceph-csi
- CRUSH
- NVMe
Features
Replication across failure domains
Data is stored several times on servers in separate failure domains. Losing a server or rack does not lose data.
Performance to measure
Node sizing across CPU, memory, NVMe and network, a dedicated storage network and tuning based on measurements.
Many access paths
Natively via RBD, over NVMe/TCP for hypervisors or classic iSCSI.
Kubernetes integration
Persistent volumes through ceph-csi, with dynamic provisioning and snapshots.
Snapshots and clones
Capture consistent points in time and clone volumes in seconds.
Storage classes
Different profiles for performance, availability and efficiency.
Use cases
01
VM disks
The backbone for OpenStack, Proxmox VE, KubeVirt and other KVM platforms.
02
Persistent volumes
Databases and stateful applications on Kubernetes.
03
Replacing SANs
A scalable successor to traditional SAN systems, without vendor lock-in.
Services
Let's talk about your infrastructure.
An architecture review, a new environment from the ground up or support in operations: talk directly to the engineers who will deliver it.