Messages & Announcements

  • 2013-04-07:  Tusker login node outage, service restored
    Category:  General Announcement

    On Sunday, the Tusker login node, tusker.unl.edu, had a software issue causing SSH login failures. The service is now running normally.

    Fixing the issue required a reboot of the login node. Running jobs were not affected.


    On Sunday, the Tusker login node, tusker.unl.edu, had a software issue causing SSH login failures. The service is now running normally.

    Fixing the issue required a reboot of the login node. Running jobs were not affected.

  • 2013-03-07:  Tusker back open with trepidation
    Category:  General Announcement

    Dear Tusker User:

    Since yesterday's Tusker shutdown, we have verified that file system integrity is in tact -- it appears there is no data loss as a result of the recent outages. Now the bad news: the root cause has not been resolved. We have taken some minor steps that we hope will help, but neither Dell nor Terascala are able to provide a complete solution at this time. They are working together to find such a solution.

    Now what? This has been an intermittent problem -- many users' jobs have not failed because of it to date. We will thus open Tusker back up for use, in the hopes that the above will remain true, while we work toward two possible resolutions: 1) either Dell and/or Terascala are able to resolve the problem and provide steps for a fix; 2) we are rolling our own Lustre filesystem on separate hardware. When a vendor is unable to add value, I believe it is only rational to investigate a vendor-free solution. The state of Nebraska will not allow me to take bets on which solution will be ready first; either way, final implementation will likely require some time and a further downtime.

    Please let us know immediately if you encounter any further issues on Tusker. We'll do our best to resolve this as quickly as possible; I do apologize for the inconvenience and frustration this has caused.

    Best regards,
    David Swanson


  • 2013-03-06:  OSG Summer School June 24-27
    Category:  General Announcement

    With apologies for the previous truncated mailing.

    ANNOUNCING THE 2013 OPEN SCIENCE GRID USER SCHOOL!

    If you could access thousands, maybe millions, of hours of computing, how
    would it transform your research? What discoveries would you make?

    We are looking for qualified students to attend the 2013 Open Science Grid
    (OSG) User School, where they will learn how to use high-throughput
    computing to harness vast amounts of computing power for research.

    Using lectures, discussions, roleplays, and lots of hands-on work with OSG
    experts in high-throughput computing, students will learn how HTC systems
    work, how to run and manage many jobs and huge datasets to implement a full
    scientific computing workflow, and where to turn for help and more info.

    Worried about costs? Successful applicants will get financial support to
    attend the OSG School (June 24-27) at the beautiful University of Wisconsin
    in Madison. Plus, some students will receive financial support to attend
    XSEDE13 (July 22-25) in San Diego, California.

    Ideal candidates are science, technology, engineering, and mathematics
    (STEM) graduate students whose research demands large-scale computing.
    Also, advanced undergraduates are encouraged to apply. Others may apply
    too; funding is tight this year, but we consider all great candidates!

    IMPORTANT DATES

    Application Period: March 4-29
    OSG User School: June 24-27
    XSEDE13 Conference: July 22-25

    MORE INFORMATION AND APPLICATIONS

    Web: https://www.opensciencegrid.org/bin/view/Education/OSGUserSchool2013
    Email: osg-school-2013-info@opensciencegrid.org

    Please forward this announcement to help us reach potential students. And
    consider posting our flyer where appropriate:

    https://www.opensciencegrid.org/twiki/pub/Education/OSGUserSchool2013/2013-osg-user-school-flyer.pdf


  • 2013-03-06:  Tusker: Unplanned Downtime: Dell/Terascala Filesystem outage
    Category:  System Failure

    Tusker is down for maintenance. The Dell/Terascala file system has experienced repeated failures the last several days. This system provides /work -- data loss is currently not expected. Work is in progress with the vendor to correct this situation. Existing jobs will be allowed to finish if possible; no new jobs will be deployed until the condition of the /work filesystem improves.

    This is an unplanned outage. Further details will be posted online until the system is back up. We apologize for this inconvenience. If you have urgent needs, please let us know and we will attempt to accommodate you if possible. Firefly and Sandhills are not affected by this downtime.


  • 2013-03-05:  Tusker /work interruption, service restored
    Category:  System Failure

    On Tusker, the Lustre filesystem for /work experienced an issue at approximately 4:11am Tuesday morning. It was resolved at 8:50am. During this time, jobs accessing /work may have failed with I/O errors.


    On Tusker, the Lustre filesystem for /work experienced an issue at approximately 4:11am Tuesday morning. It was resolved at 8:50am. During this time, jobs accessing /work may have failed with I/O errors.