System Status

  • UPDATE - 11/13/2018 12:10 - 

    Grace, Omega and Farnam temporarily lost contact with the Loomis GPFS storage system due to a networking issue. The issue has been resolved but most running jobs crashed and should be checked on. Sorry for the inconvenience.

    11/13/2018 - 12:05 - 

    Loomis storage mounted on Grace, Omega and Farnam is currently unavailable. Logins to Grace and Omega will be unavailable during this time. Updates to this issue will be posted here.  

Services Status

Node Cluster Status
Google Drive Globus Connector N/A Available
transfer-grace.hpc.yale.edu* Grace Available
transfer-farnam.hpc.yale.edu* Farnam Available
transfer-omega.hpc.yale.edu* Omega Available
transfer-ruddle.hpc.yale.edu* Ruddle Available

* when unavailable, the associated Globus endpoint will also be unavailable.

Cluster Maintenance

To perform critical updates and minimize downtime, regular maintenance will be performed on each cluster on a rotating schedule. Scheduled maintenance periods typically start on a Monday and run through the end of the following Wednesday. During maintenance, logins will be disabled, jobs will not run and cluster storage may be unavailable. Communication will be sent to users both 4 weeks and 1 week prior to the maintenance period.

Scheduled maintenance will be canceled if insufficient justification exists prior to the planned start. Communication will be sent immediately if a maintenance window is being canceled.

Schedule

  • Nov 4-8 2018 All Clusters
  • Nov 4-9 2018 Ruddle
  • Dec 10-12 2018 Milgram
  • Feb 1 2019 Omega scratch permanently deleted
  • Feb 4-6 2019 Grace
  • Mar 4-6 2019 Farnam
  • Apr 8-10 2019 Ruddle
  • May 6-8 2019 Milgram
  • Jun 3-5 2019 Grace
  • Aug 5-7 2019 Farnam
  • Sep 9-11 2019 Ruddle
  • Oct 7-9 2019 Milgram
  • Nov 4-6 2019 Grace
  • Dec 2-4 2019 Farnam