Snyder Scratch Move & Maintenance
Link to update at November 7, 2017 6:42pm EST UPDATE:
As of 6:42pm EST, engineers have completed maintenance and have returned the Snyder cluster back to normal service. All queues have been enabled and jobs have resumed scheduling. Please report any issues to rcac-help@purdue.edu
Link to original posting ORIGINAL:
The Snyder scratch storage will be moving to a new storage system on Tuesday, November 7, 2017. There will not be any automatic transfer of files from your old scratch space to your new scratch space. You will find there are two new environment variables to assist you in a smooth transition to this new space:
- $CLUSTER_SCRATCH_NEW (new scratch space)
- $CLUSTER_SCRATCH_OLD (old/existing scratch space)
The new scratch space ($CLUSTER_SCRATCH_NEW) is already available on all Snyder submission front-ends and compute nodes. During the maintenance on Tuesday, November 7, 2017, the $CLUSTER_SCRATCH variable will switch from matching $CLUSTER_SCRATCH_OLD to matching $CLUSTER_SCRATCH_NEW.
The old scratch space will remain available until December 12 through the $CLUSTER_SCRATCH_OLD variable. However, this scratch space will be removed from Snyder at that point. Also on December 12, the $CLUSTER_SCRATCH_NEW and _OLD variables will be removed.
Please be sure to copy any files you need from the old path to the new path.
During the maintenance Tuesday, November 7, 2017 at 8:00am EST, Snyder will also have the operating system patched, minor software upgrades, and improvements to Thinlinc support. Any PBS jobs which request a walltime which would take them past Tuesday, November 7th, 2017 at 8:00am EST will not start and will remain in the queue until after the maintenance is completed.