We have implemented a fix and will be monitoring the queues to ensure the fix had the intended outcome.
Posted about 1 year ago. Jun 07, 2018 - 17:05 MDT
Some users jobs are being held in the queue due to the reason of (QOSGrpNodeLimit) when there are nodes available within the partition to run. We are currently investigating this issue and are working with the vendor to resolve the issue.