Migration Info

8/14/2018

Dear Individual PI Partition owners,

The Research Computing team is preparing the migration of the individual PI partitions to the New Discovery cluster.  The new discovery cluster has significant improvements in both functional and operational capabilities.

Changes / Features

  • slurm updated to current release (slurm-17.11.6)
  • Node types will be individually allocable by general resources and trackable resources (GRES and TRES) i.e. GPU, PHI, Memory
  • Base OS updated to CentOS 7.5 from CentOS 6.x
  • Software (latest versions) has been compiled for CentOS 7.5  available at /shared/centos7
  • Currently available software in /shared/apps can be made available by adding the ‘legacy’ module (modules add legacy)
  • Login node change, new nodes: login-00.discovery.neu.edu, login-01.discovery.neu.edu
  • x11 forwarding support by slurm for jobs.
  • Users will not be able to ssh to nodes unless they have a slurm-allocation on the node in question
  • File transfer node for transferring files to and from the Discovery cluster.

We need to hear from you to schedule this phase of the discovery cluster migration.  Please let us know if you have any limiting factors to migrate your partitions.  RC’s goal is to complete this process by the end of September.  By meeting this deadline, RC will be able to focus efforts on the new Discovery rather than supporting the legacy cluster.  Also, please review the new Discovery guide for cluster changes and access information

What you need to know about job submission during this transition:

  • Once the nodes of the partitions scheduled to be moved  are put in drain state the following things will happen:

o   Currently running jobs will run to completion

o   No new jobs will be launched.

o   Jobs submitted after the partition is in drain state will never launch on the old discovery cluster

  • Once the partition nodes are in drain state, please cancel all your pending jobs and relaunch them on the new discovery.

It is highly advisable that you start familiarizing yourself with the new discovery prior to this migration. 

The general partition migration schedule can be found here

 

The RC team