RACK TRAIL
Solutions
VMware MigrationOpenStack at scaleProxmox at scalePrivate AICloud Cost OptimizationManaged Private CloudLarge Scale MigrationBig Data InfrastructureConfidential Computing InfrastructureCephKubernetes WorkloadsCloud Infrastructure for Startups
Why RacktrailGroundworkAbout Talk to an Engineer
Products · Private Cloud

Private cloud, without the private cloud project.

Dedicated OpenStack or Proxmox environments, deployed and operated for you. Full root access, standard APIs, and hardware that belongs to your workload alone.

What you get

Dedicated hardware

Your nodes, not a slice of someone else's.

Your own control plane

A full OpenStack or Proxmox deployment, not a multi-tenant portal with your name on a tab.

Root access

To the hypervisor, the network config, and the storage layer.

Ceph-backed storage

Block and object, replicated across failure domains.

Software-defined networking

Private networks, floating IPs, security groups, VPN termination.

Monitoring and alerting

Prometheus and Grafana, with the dashboards handed to you.

OpenStack or Proxmox — your call

Most providers made this decision before you arrived, because they only run one. We'll make it with you.

OpenStack
Proxmox
Best for
Multi-tenant clouds, API-driven infrastructure, cloud-native platforms
VM consolidation, VMware replacement, straightforward virtualisation
Tenancy
Full multi-tenancy with projects and quotas
Single-tenant or lightly segmented
API
Comprehensive, mature, Terraform-native
Functional REST API, lighter tooling ecosystem
Operational weight
Higher — more components, more capability
Lower — fewer moving parts
Migrating from VMware
Good fit at scale, more re-architecture
Fastest path, closest conceptual mapping
Kubernetes underneath
Strong — Cluster API, native integration
Workable, less integrated

Not sure?

That's the normal state of affairs. Tell us what you're running now and we'll tell you which one we'd pick and why.

How it's built

Dedicated compute nodes with redundant power and networking. Ceph clusters replicated across failure domains. Redundant top-of-rack switching and redundant upstream transit. You scale by adding nodes, and you know what each one costs before you add it.

Failure domains · schematic compute ×4 · ceph osd ×6 · tor ×2 per rack
RACK A RACK B RACK C OFFLINE replication factor 3 one rack may fail

Where it runs

In the region your residency and latency requirements call for — or your own facility, if that's what compliance demands. Your constraints decide placement, not our map.

Sweden

Stockholm

Available
Sweden

Falkenberg

Available
Germany

Frankfurt

Available
United Kingdom

London

Available
United States

Washington, D.C. Metro

Available
United States

New York Metro / Secaucus

Available
United States

Silicon Valley / San Jose

Available
Singapore

Singapore

Available
Japan

Tokyo

Available
India

Mumbai

Available
Nepal

Kathmandu

Available
colo or on-prem

Your facility

On request

What stays yours

Your images, your configuration, your Terraform and Ansible, your data. All of it standard, all of it documented, all of it exportable. We publish the migration path off Racktrail in the same documentation that tells you how to run on it.

If you leave, we’d rather you left cleanly and told people we were straight with you.

Good fit for

Replacing VMware after the Broadcom licensing changes

see how the migration works →

Cutting a hyperscaler bill without losing capability

Regulated workloads with hard residency requirements

MSPs and providers building their own offering on top

Frequently asked

How long does provisioning take?

It depends on the hardware, the region and the size of the environment. We'll give you a date once we've scoped it, rather than a range that turns out not to apply to you.

Can we bring our own hardware?

Yes. We'll deploy and operate on hardware you already own, in your facility or a colo you already use.

What do you manage, and what do we?

Whatever split you want. Fully managed, co-managed, or we support and you operate. The boundary goes in the contract so there's no ambiguity at 3am.

What happens if we want to leave?

We hand over documentation, configuration and data in standard formats, and help you plan the move. Nothing is held in a proprietary format you would have to unpick.

Tell us what needs to run.

Send us the workload, the constraints, and the region it has to live in. An engineer — not a sales rep — will tell you honestly whether we're the right fit.