Packet loss on the GlobalConnect uplink in STO
Network — transit & peering — STO
Timeline
-
Resolved
The GlobalConnect uplink in STO has been clean for 5 minutes with the session restored. Total duration of the degradation: 42 minutes. No machine lost connectivity; some traffic saw higher latency during the detour.
-
Monitoring
GlobalConnect reports the card replaced. We have re-enabled the session and are watching error counters before calling this resolved.
-
Identified
GlobalConnect has confirmed a faulty line card on their side of the STO handover. We have withdrawn our prefixes from that session, and all traffic is leaving through Arelion and Netnod for now. Loss has cleared; latency to some destinations is 3–6 ms higher while the detour is in place.
-
Investigating
We are investigating packet loss of around 5% towards a subset of destinations from STO. Alerts fired at 22:44 UTC on the GlobalConnect uplink; the Arelion uplink and the Netnod peering are clean. Machines remain reachable.
Times are shown in your time zone ().
Related pages
- Service statusLive status of every gpuserver.io component and data centre, probed every 60 seconds from five cities, with 90-day uptime and the incident log since 2022.
- Incident historyEvery incident and maintenance window on gpuserver.io since monitoring began in September 2022, month by month, with its timeline and post-incident review.
- Service level agreementThe 99.9% commitment: what counts as downtime, how it is measured from outside, five minutes of term back per minute lost, and the exclusions in full.
- NetworkUnmetered ports up to 25 Gbit/s, two carriers and an IX per site, always-on DDoS filtering, routed IPv6 — and the four things we do not offer, stated up front.