[SOLVED] Colossus Maintenance Downtime on Friday between 09:00 - 11:00 CET

Lately, the usage of Colossus has increased, and most of the time every node is busy running the jobs.  The Infiniband network on one of the storage nodes has been unstable lately, causing decreased performance and lower availability. We will attempt to correct this on Friday between 09:00 - 11:00 CET.

 

We will place a reservation on the queue system during the aforementioned timeframe. This way the new jobs that overlap the timeframe will not start, while allowing currently running jobs to finish.

 

Submitted jobs that are not specified to finish before Friday at 09:00 will remain queued until the maintenance is finished.

 

We are sorry for the inconvenience.

 

TSD@USIT

Published Dec. 5, 2018 2:18 PM - Last modified Dec. 7, 2018 11:07 AM