Current status of Maths computing facilities...

September 23rd: bazooka Hadoop cluster powered off to reduce heat load, lovelace is backup up, all other systems and services operating normally

The compute server has now reverted to its original Ubuntu server configuration and is back up and available for use; services including graphical logins and desktop environments, x2go and Jupyter Hub that require a desktop type Ubuntu installation have been moved to another system better suited to this mode of operation.

archimedes has been repaired with a new hard disk and rebuilt but is not yet ready for general use.

The bazooka Hadoop cluster was shut down at 2:30pm Friday afternoon, August 7th, since it has not been used for several weeks and is a major source of heat in the server room. Also shut down at the same time was the combined MySQL/PostgreSQL database server which produces a substantial amount of heat but this has since been powered back on early Saturday morning.

If there is demand for it, the bazooka Hadoop cluster will be powered back on but we have for some time had an unofficial policy of powering off unused equipment in the interests of reducing energy consumption, heat generation, loads on cooling systems and, frankly, with the future of this planet in mind.

September 5th: known issues

Current known problems are listed below:

March 20th: legacy known issues

As always, hardware faults can occur when systems that have been powered on for years are first powered off and then back on again a short while later and the following equipment were casualties of the scheduled power-downs on March 3rd and 11th:

  • fira: this elderly HP workstation in the Stats Linux cluster is awaiting two replacement disks but since the new madul, midal and model large compute servers which were introduced in February and March effectively supercede it, repair of this seldom-used system is not a high priority.

Andy Thomas

Research Computing Manager,
Department of Mathematics

last updated: 23.9.2020