All compute nodes and login nodes of Owens, Oakley, and Ruby clusters will need to be rebooted for kernel upgrades because of security vu

Jobs requesting Lustre are rejected by qsub

Date: 
Friday, August 15, 2014 - 11:30pm
Supercomputer: 

On both production clusters, we have begun rejecting jobs that request the use of Lustre or $PFSDIR in order to reduce job failures caused by the triggering of a bug that crashes the filesystem. If you have a GPFS allocation, you may if appropriate want to move your data there in order to maintain productivity while the Lustre service is in a degraded state.