Monthly maintenance will take place on November 3rd. Additionally, MGHPCC will be performing power upgrades on the even side of Row 8A where much of our computer resides. A further upgrade will take place Dec. 8th on the odd side.
A list of the affected partitions is provided at the bottom of this notice. The nodes in those partitions will be drained prior to the work and will be powered down. Once the work is completed, those nodes will be returned to service. Current estimate is a 12 hour window. We will adjust as we know more.
MAINTENANCE TASKS
Cannon cluster will be paused during this maintenance?: PARTIAL OUTAGE/YES
FASSE cluster will be paused during this maintenance?: PARTIAL OUTAGE/YES
Power work on Row 8A Even
Slurm upgrade to 25.05.4
Block repo.anaconda.com cluster wide
Audience: Anyone attempting to use repo.anaconda.com
Impact: This change should not impact your Python workflow on the cluster. But if it does, consider using the open-source channel, conda-forge, through Miniforge distribution to install Python packages. This can be done by following our instructions on https://docs.rc.fas.harvard.edu/kb/python-package-installation/
Change Slurm User to Local User
Login node reboots (morning)
Netscratch cleanup ( https://docs.rc.fas.harvard.edu/kb/policy-scratch/ )
AFFECTED PARTITIONS
Nov. 3, 2025 - All Day Power Work
Partial or Full Outage Apples to:
arguelles_delgado_h100
bigmem
dvorkin
eddy
enos
gpu
gpu_h200
gpu_requeue
hsph
hsph_gpu
intermediate
itc_cluster
joonholee
jshapiro
kempner_dev
kemkpner_eng
kempner_requeue
mweber_compute
mweber_gpu
olveczky_sapphire
sapphire
seas_compute
seas_gpu
serial_requeue
yao
yao_gpu
yao_priority
test