Dear NERSC Users: Mounting Perlmutter scratch at scale revealed some unanticipated file system performance issues. We've seen a steep decline in write performance and sporadic I/O errors on login nodes. NERSC and HPE engineers are working together to try to find what is happening and how to fix it, but no solutions have yet been found. We have therefore kept the scratch file system licence hold in place, to ensure that any jobs currently requesting the scratch file system would not be released and see poor performance. I do not currently have a time frame for when this issue might be resolved, but hope to be able to provide an update on Monday. In the meantime, please continue to use the Community File System (CFS) as your primary file system for jobs on Perlmutter. Regards, -Rebecca -- Rebecca Hartman-Baker, Ph.D User Engagement Group Leader National Energy Research Scientific Computing Center | Berkeley Lab rjhartmanbaker@lbl.gov | phone: (510) 486-4810 fax: (510) 486-6459 Pronouns: she/her/hers _______________________________________________ Users mailing list Users@nersc.gov