All 6 data centres operational

Paid in crypto · No identity check · Root access in under 5 minutes

Critical Resolved Review published

gpuserver.io unreachable

Website & configurator · Sign-in & customer area

Timeline

  1. Resolved

    Reachable since 18:24 UTC. Duration: 6 minutes. No order or payment was affected; anyone who was on the payment page simply had to reload it.

  2. Investigating

    gpuserver.io is not responding from any of our probe locations since 18:18 UTC. Machines, payments watchers and provisioning are unaffected; only the website and customer area are down.

Post-incident review ·

What happened, and what changed

Cause

The tunnel connector between the CDN edge and our origin hit a bug in its reconnect logic after the edge rotated its certificates, and stayed down instead of retrying.

Impact

The website and customer area were unreachable for 6 minutes. Payment detection, term activation, provisioning and every machine were unaffected.

What we changed

  • The connector was updated to the version containing the fix.
  • A second connector instance now runs alongside the first, so a single failure no longer takes the site offline.
  • The external probes now alert on the tunnel state directly, not only on the resulting HTTP failure.

Sign in

Console, invoices and out-of-band access.

No account yet?

There is no separate sign-up. Your account is created while you place your first order — you choose the email and the password on the payment step, and the console is open by the time the machine is.

Configure a server

Language