ARSC system downtime for all systems (all)

Menu to filter items by type

Type Downtime News
Machine All Systems linuxws pacman bigdipper fish lsi
Downtime All Future Current Past

Contents for all systems

News Items

28 Jan 2016 Unscheduled Downtime

Last Updated: Thu, 28 Jan 2016 -
Machines: pacman
Start Time: 01/28/2016 -- 07:10
  End Time: 01/28/2016 -- 22:00
    Reason: The standard_4 management node dropped offline.  Work is in progress to 
            diagnose and recover the node as soon as possible.  Users with jobs 
            running at the start of the outage have been notified.

06 Jan 2016 Scheduled Downtime

Last Updated: Wed, 16 Dec 2015 -
Machines: linuxws pacman
Start Time: 01/06/2016 -- 09:00
  End Time: 01/06/2016 -- 21:00
    Reason: The Pacman.arsc.edu system and Linux Workstations will be taken offline
            on Wednesday January 6, 2016 for scheduled system maintenance beginning
            at 9am.  The systems are anticipated to remain offline through 9pm
            on January 6th.
            Pacman user jobs with walltimes scheduled to complete by 9am on January
            6th will run as normal.  Queued jobs with walltimes which would overlap
            the 9am January 6th scheduled maintenance start time will remain
            queued, then will be released at the completion of system maintenance.

11 Dec 2015 Unscheduled Downtime

Last Updated: Mon, 14 Dec 2015 -
Machines: linuxws pacman bigdipper fish lsi
Start Time: 12/11/2015 -- 10:41
  End Time: 12/12/2015 -- 17:00
    Reason: On Friday December 11, 2015 at 10:41pm, the water pumps in the
            Butrovich Machine Room responsible for cooling the RCS HPC systems
            failed. As a result the Pacman, Fish, and Digdug $CENTER filesystems
            were powered down. Running user jobs were lost. Users with lost
            jobs were notified individually.
            The systems were back online by 5pm on Saturday December 12th.
            Please contact uaf-rcs@alaska.edu with questions regarding this
            unscheduled outage.


Back to Top