University of Cambridge Computer Laboratory - Reduced Caelum Console functionality – Incident details

GPUs experiencing major outage

Reduced Caelum Console functionality

Resolved
Degraded performance
Started 9 months agoLasted about 9 hours

Affected

Internal Services

Degraded performance from 12:23 PM to 7:11 PM, Operational from 7:11 PM to 9:02 PM

Caelum Console (server management)

Degraded performance from 12:23 PM to 7:11 PM, Operational from 7:11 PM to 9:02 PM

Updates
  • Resolved
    Resolved

  • Monitoring
    Monitoring

    A fix has been implemented for the misbehaving Caelum live state database (which had failed, filled the disk with error logs, and caused more problems).

  • Identified
    Identified

    Some functions of Caelum Console are temporarily unavailable due to a server problem which will be rectified as soon as possible.