Center for Computational Research

Date of downtime: Tuesday, January 21, 2020

Approximate time of outage: 7am-5pm

Resources affected by downtime:

UB-HPC cluster (general-compute, debug, viz, largemem, and gpu  partitions) 

Industry cluster (compute, scavenger partitions)

Faculty cluster (all partitions)

Portals: WebMO, OnDemand

What will be done:  

• BUDGET STORAGE WILL BE DECOMMISSIONED!  Any users with directories in /budgetdata MUST get their data out before January 21st at 7am.
• Update OS and reboot all cluster nodes, front end servers, and OnDemand server
• Default walltime on ub-hpc cluster changes from 72 hours to 24 hours.  Users may specify up to 72 hours for walltime on the ub-hpc cluster
• License server - operating updates and reboot
• New nodes in 'cascade' partition - includes compute, large memory, and GPU nodes in one partition (not available until week of Jan 27)
  
  More details
  
  

Jobs will be held in the queue during the maintenance downtime and will run after the updates are complete.

If you have  any questions or concerns please e-mail ccr-help_at_buffalo.edu