Owens
Upgrade to SLURM at 9AM on Dec 2
It is scheduled to have an update to SLURM scheduler at 9AM on Wednesday, December 2nd. The upgrade will have no impact on running jobs and will only make the SLURM scheduler unavailable for user commands for approximately 3 minutes. This update is from 20.02.5 to 20.02.6, and includes a few critical security patches and bug fixes.
owens slurm migration
OSC will be migrating the owens cluster from torque/moab to slurm on Dec. 15, 2020. We encourage users to participate in the early user program from Nov. 23 to Dec. 14 to test their workflows with the new scheduler. No registration needed.
Jobs submitted in the owens early user environment will not be charged.
For more info: https://go.osu.edu/Bzkw
System Downtime December 15 2020
A downtime for all OSC HPC systems is scheduled from 7 a.m. to 9 p.m., Tuesday, December 15, 2020. The downtime will affect the Pitzer and Owens Clusters, web portals, state-wide licenses, and HPC file servers. Login services will not be available during this time, including MyOSC.
In preparation for the downtime, the batch scheduler will begin holding jobs that cannot be completed before 7 a.m., December 15, 2020.
Environment changes in Slurm migration
As we migrate to Slurm from Torque/Moab, there will be necessary software environment changes.
Decommissioning old MVAPICH2 versions
Old MVAPICH2 including mvapich2/2.1, mvapich2/2.2 and its variants do not support Slurm very well due to its life span, so we will remove the following versions:
- mvapich2/2.1
- mvapich2/2.2, 2.2rc1, 2.2ddn1.3, 2.2ddn1.4, 2.2-debug, 2.2-gpu
As a result, the following dependent software will not be available anymore.
HOWTO: Tune VASP Memory Usage
This article discusses memory tuning strategies for VASP.
Data Distribution
Typically the first approach for memory sensitive VASP issues is to tweak the data distribution (via NCORE or NPAR). The information at https://www.vasp.at/wiki/index.php/NPAR covers a variety of machines. OSC has fast communications via Infiniband.
OSC internal network problems 25 Sept. 2020
OSC is currently experiencing problems with its internal network. Interactive sessions may be slow or unresponsive, but running jobs should not be affected.
Pitzer expansion and slurm migration
OSC has expanded Pitzer Cluster approximately tripling the peak capacity.