ARSC system downtime for all systems (all)
Menu to filter items by type
Contents for all systems
Start Time: 01/08/2014 -- 08:00 End Time: 01/22/2014 -- 08:00 Reason: All LSI systems will begin system maintenance on Wednesday, January 8, 2014. Maintenance is planned to continue through Wednesday, January 22nd at the latest. The LSI systems will remain inaccessible for the entire span of the maintenance period. All user jobs will be killed on January 8th at 8am. If you would like to receive your job output BEFORE the downtime, please kill your job(s) and download the output prior to January 8, 2014.
Start Time: 12/10/2013 -- 08:00 End Time: 12/11/2013 -- 10:30 Reason: The $ARCHIVE filesystem, bigdipper, was taken offline due to an unexpected hardware failure on Tuesday December 10th. Access to $ARCHIVE files, /project files, and Web Services hosted by bigdipper were offline.
Machines: pacman bigdipper
Start Time: 12/08/2013 -- 05:30 End Time: 12/09/2013 -- 09:00 Reason: The $ARCHIVE storage server, bigdipper, began displaying signs of hardware instability similar to the issues on 12/01. After several restores and failures, the replacement component received last week was installed. Bigdipper is back online and is being monitored closely for any subsequent issues. Users experienced hanging prompts on pacman login nodes and unresponsiveness to Web Services during this outage.
Machines: linuxws pacman bigdipper fish
Start Time: 11/30/2013 -- 10:54 End Time: 12/2/2013 -- 13:00 Reason: Hardware failure on bigdipper. This system provides storage services for $ARCHIVE, Web servers, and other purposes. Oracle has provided diagnostics, and it appears a replacement part needs to be installed by a field engineer. A follow up downtime is pending, possibly with short notice, to replace the failed component. Pacman users should consider utilizing the transfer queue for file transfer to and from $ARCHIVE, to lessen the chance of transfer interruption due to a downtime.
Start Time: 11/24/2013 -- 05:00 End Time: 11/24/2013 -- 08:00 Reason: UAF is replacing networking hardware in the Duckering Building. Expect multiple 30-60 second outages.
Start Time: 11/14/2013 -- 18:00 End Time: 11/15/2013 -- 08:00 Reason: Duckering Building power outage.
Start Time: 11/13/2013 -- 14:25 End Time: 11/13/2013 -- 15:24 Reason: The pacman 4-core head node crashed. User jobs running at this time were terminated. Users have been notified.
Start Time: 11/07/2013 -- 23:00 End Time: 11/08/2013 -- 08:10 Reason: Duckering Building power outage.
Start Time: 10/29/2013 -- 09:02 End Time: 10/29/2013 -- 20:35 Reason: Due to an unplanned power outage on the University of Alaska Fairbanks campus this morning, all jobs running on the fish system were lost. Users with lost jobs were notified individually.
Machines: linuxws pacman bigdipper
Start Time: 10/29/2013 -- 09:02 End Time: 10/29/2013 -- 12:12 Reason: Due to an unplanned power outage on the University of Alaska Fairbanks campus this morning, all jobs running on the pacman system were lost. Users with lost jobs were notified individually.