System Updates Archive

  • Brief Outage on Grace

    Tuesday, June 23, 2015 - 3:15pm

    The Grace cluster experienced a brief outage today at 3:15 pm.  Any scheduled job running on Grace at this time was likely impacted and will need to be restarted.   The HPC team will continue to monitor the situation and updates will be posted here as more information becomes available.

    We apologize for any inconvenience this may have caused and as always, if you have any questions or concerns please don’t hesitate to contact us at hpc@yale.edu

  • hpc@yale.edu email address bouncing

    We have discovered that our support email address, hpc@yale.edu, is bouncing back to the sender.  We are currently working with the email team to resolve the issue and it should be working shortly.  In the mean time, if you have an urgent issue, please contact the research support team directly (Andy, Steve, Rob or Jason) Their email addresses can be found to the right of this message.  Apologies for any inconvenience this may have caused.

  • GPFS / Grace Cluster back up

    Friday, June 12, 2015 - 10:00pm

    The GPFS filesystem is up and running normally.  Any scheduled  jobs previously running on Grace or any other job using data from /gpfs on other clusters was likely impacted and will need to be restarted.  

    We apologize for any inconvenience this may have caused and as always, if you have any questions, concerns or comments please don’t hesitate to contact us at hpc@yale.edu.

  • Brief Network Outage - Sunday morning - Low Impact

    Sunday, June 14, 2015 - 5:30am

    Yale ITS will be performing network maintenance affecting all network connections to and from the ITS Data Centers on Sunday, June 14, between 5:30 a.m. and 6:30 a.m. The HPC Clusters will be inaccessible during this time, however all jobs will continue to run.  Interactive jobs may experience a disruption.  

    If you have any questions or concerns, please email the HPC team at hpc@yale.edu.

  • BulldogN Maintenance Postponed

    Friday, June 5, 2015 - 12:00pm

    We have decided to postpone the maintenance window for Bulldogn that was scheduled for Monday June 8th. Another downtime will be required in a few weeks for electrical power work in our West Campus Data Center and in an effort to avoid multiple interruptions we have chosen to consolidate maintenance windows.  The precise date has yet to be determined.

    In the meantime, we may contact individual users in order to arrange to migrate their home directories while the cluster is operating.

    To see the latest updates please visit the Status Page on the Yale Center for Research Computing website.
    If you have any questions, concerns or comments, please don’t hesitate to contact us at hpc@yale.edu.
     

  • Grace Cluster Back Online

    Saturday, May 23, 2015 - 8:00am

    All storage and nodes as part of the Grace expansion are available for use. An additional 90 general use nodes are available as well as an additional 500 TB of storage.   Dedicated hardware is also available and details have been communicated directly to the group leaders.

    We apologize for any inconvenience this may have caused and as always, if you have any questions, concerns or comments please don’t hesitate to contact us at hpc@yale.edu.

  • Grace Cluster and GPFS Filesystem Back Online

    Friday, May 8, 2015 - 5:30pm

    Maintenance to the Grace cluster and GPFS Filesystem is now complete.  The cluster is back online and available for access.  We apologize for any inconvenience resulting from the delay.  

    If you have any questions,  concerns or comments, please don’t hesitate to contact us at hpc@yale.edu.

  • CONTINUED DELAY: Grace Cluster and GPFS Filesytem

    Friday, May 8, 2015 - 9:30am

    The Grace Cluster and GPFS Filesystem coming back online has been delayed.  The cluster has been experiencing network problems and so far the issue has been narrowed to the storage network.   There is no impact to the underlying filesystem or storage of data.

    The team will continue to addess the issue over the weekend and will continue to post updates to the website as more information is available.  At this time we are not expecting resolution before Monday.

    If you have any questions,  concerns or comments, please don’t hesitate to contact us at hpc@yale.edu

  • Power Outage at West Campus

    Thursday, May 7, 2015 - 1:00pm

    A brief power outage at West Campus resulted in bringing many Omega Cluster nodes offline.  The cluster has been restored and is currently running however jobs may have been impacted.  If you are currently using the Omega cluster we are advising you to check your jobs to determine if they need to be restarted.

    If you have any questions,  concerns or comments, please don’t hesitate to contact us at hpc@yale.edu.

  • CONTINUED DELAY: Grace Cluster and GPFS Filesytem

    Thursday, May 7, 2015 - 4:00am

    The Grace Cluster and GPFS Filesystem coming back online has been delayed.  Currently there is no estimated time for resolution but the team is working hard to complete the maintenance and updates will be posted here.

Pages