Oldwiki.scinet.utoronto.ca:System Alerts

From oldwiki.scinet.utoronto.ca
Revision as of 10:07, 18 December 2014 by Rzon (talk | contribs) (→‎System Status)
Jump to navigation Jump to search

System Status

upGPC upTCS upSandy upARC upFile System
upGravity upP7 being brough back upBGQ upHPSS

Thu Dec 18 9:30:00 EST 2014: Both BGQ systems shutoff due to a cooling issue. Systems are being brought back up.

Fri Dec 12 11:52:52 EST 2014: BGQ Dev system upgraded to 2 full-racks.

Fri Dec 5 08:25:48 EST 2014: City has just confirmed that water has been restored. Staff are on-site and restarting cooling systems. Users should have access to compute systems before noon.

Fri Dec 5 06:51:56 EST 2014: City has reported that water should be restored by 8AM. If they're on schedule, it could still take a few hours after that to restart cooling systems, power-up and test storage etc

Thu 4 Dec 2014 16:05:07 EST: Some systems are back up, but only until tonight when the advertised shutdown will still happen, starting at around 9PM. Only short jobs, that fit in the short time before the systems are taken down, will run. Filesystems are up, as well as devel nodes on all platforms. BGQ will remain down until after the water repairs.

Thu Dec 4 14:03:24 EST 2014: Systems abnormally shutdown due to loss of plumbing to secondary loop. Still investigating.

ALL SYSTEMS TO BE SHUTDOWN ON THURSDAY- On Thursday Dec 4, at 9PM EST, all systems will need to be shutdown. The city of Vaughan has advised us that the city water supply will be turned off in order to fully fix the problem that occured on Nov 21. With no water supply we cannot cool the datacentre, hence the shutdown. We expect all systems to be back up on Friday Dec 5, at around 11AM.


(Previous messages)