Affects
- UpdateMarch 04, 2024 at 4:19 PMCompletedMarch 04, 2024 at 4:19 PM
The Slurm upgrade to 23.11.4 was completed successfully during maintenance. However a complication with the automation of Slurm's cryptographic keys occurred during the upgrade which caused nodes to lose the ability to talk to the Slurm master. The Slurm master therefore viewed those nodes as down and requeued their jobs.
All jobs on Cannon and FASSE were requeued.
This is deeply regrettable but the chain of events which caused this could not be foreseen.
To check the status of your jobs, see the common Slurm commands at:
https://docs.rc.fas.harvard.edu/kb/convenient-slurm-commands/#Information_on_jobs
FAS Research Computing
- CompletedMarch 04, 2024 at 4:15 PMCompletedMarch 04, 2024 at 4:15 PMMaintenance has completed successfully
- UpdateMarch 04, 2024 at 3:56 PMIn progressMarch 04, 2024 at 3:56 PM
Due to unforeseen issues with updates, maintenance will run long. ETA 11:15
- In progressMarch 04, 2024 at 12:00 PMIn progressMarch 04, 2024 at 12:00 PMMaintenance is now in progress
- PlannedMarch 04, 2024 at 12:00 PMPlannedMarch 04, 2024 at 12:00 PM
FASRC monthly maintenance will take place Monday March 4th, 2024 from 7am-11am
NOTICES
2024 training sessions are available. Topics so far include New User Training, Getting Started on FASRC with CLI, Getting Started on FASRC with OpenOnDemand, Installing and using software, GPU Computing, Advanced cluster usage, Parallel job workflows, and other advanced topics. To see current and future training sessions, view our calendar at: https://www.rc.fas.harvard.edu/upcoming-training/
For these and other events such as Office Hours, view our entire events calendar at: https://www.rc.fas.harvard.edu/upcoming-events/
TIP: Subscribe to receive status page notices at https://status.rc.fas.harvard.edu/ (click Get Updates for options).
MAINTENANCE TASKS
Cannon cluster will be paused during this maintenance?: YES
FASSE cluster will be paused during this maintenance?: YES
Slurm upgrade to v 23.11.4
-- Audience: All cluster users
-- Impact: The scheduler will be unavailable during maintenance. This is likely to require the entire maintenance window. There is a small possibility that this may go over time. Please watch the Status Page for updates.
-- Jobs will be paused to accommodate this upgrade
Infiniband Nvidia MQM9700 firmware update to the latest version 3.11.3002
-- Audience: All cluster users
-- Impact: No direct impact (this is networking firmware, not GPU firmware)
-- Jobs will be paused to accommodate this update
Internal services updates
-- Audience: FASRC internal services including: foreman, atlantis, puppet, terraform
-- Impact: No user-facing impact
Login node and OOD/VDI reboots
-- Audience: Anyone logged into a login node or VDI/OOD node
-- Impact: Login and VDI/OOD nodes will rebooted during this maintenance window
Scratch cleanup ( https://docs.rc.fas.harvard.edu/kb/policy-scratch/ )
-- Audience: Cluster users
-- Impact: Files older than 90 days will be removed. Please note that retention cleanup can run at any time, not just during the maintenance window.
Thanks,
FAS Research Computing
Dept. Website: https://www.rc.fas.harvard.edu/
Documentation: https://docs.rc.fas.harvard.edu/
Status Page: https://status.rc.fas.harvard.edu/