Due to an administrative error during the suspension of PBS jobs for Pleiades, Electra, and Aitken Cascade Lake nodes, most suspended jobs could not be resumed.

Jobs that could be re-queued were prioritized to start again as soon as possible. Other jobs that could not be re-queued were deleted. If your job was deleted, please send a ticket to support@nas.nasa.gov to provide the replacement job ID so we can raise its priority.

We apologize for the inconvenience. If you have any questions, please contact the Control Room at (800) 331-8737, (650) 604-4444, or support@nas.nasa.gov.

Original Notification

There will be a suspend/resume for Pleiades, Electra, and Aitken, and dedicated time for Lou, Endeavour, and V100 GPU nodes, on Wednesday, October 13, from 10:00 a.m. to 11:59 p.m. (Pacific Time) to facilitate system patching.

The following services will be affected:

• Pleiades, Electra, Aitken, and Endeavour will not be available during this period, jobs cannot be submitted, and there will be no access to the Lustre or NFS filesystems.
• Jobs on Pleiades, Electra, and Aitken will be suspended at the beginning of the period and will be resumed at the conclusion of the period. There should be no other impact to these jobs.
• Pleiades front ends (PFEs) and Lou front ends (LFEs) will be unavailable during this period.

In addition, during this time the pbspl4 system will be upgraded to PBSPro version 20. pbspl4 will then match the PBSPro version of all other systems, which were upgraded to version 20 several months ago. After the upgrade you will be able to run PBS commands from PFE hosts for jobs on the Pleiades V100 GPU nodes and Endeavour systems.

If you have any questions, please contact the Control Room at (800) 331-8737, (650) 604-4444, or support@nas.nasa.gov