Sunday, March 5, 2017 - This issue appears to be caused by a large number of complicated jobs being submitted to the system. This is causing the scheduler to slow down and thus significant time being taken to schedule new jobs. We have implemented a maximum job limit on the Argon cluster to mitigate this issue and are working with the user who caused the issue to mitigate it further.
9:00PM, Friday, March 3, 2017 - Scheduling performance has returned to normal.
3:45 PM, Friday, March 3, 2017 - Argon is currently experience degraded scheduling performance. We have had reports of job scheduling taking 15-40 minutes instead of the typical few seconds. We are investigating the cause of this issue.
If you have questions please contact us at firstname.lastname@example.org