DokuWiki

User Tools

Site Tools

Trace: • 97 • 40 • 58 • 52 • 166 • 98 • 85 • 38 • 32 • 162
cluster:162


Back

  • Jobs can be submitted from any node.
  • cottontail is primary scheduler login node.
  • You can login in to any tail node directly (via ssh).
  • All nodes are CentOS 6.x with some exceptions noted.

Test Queue

  • Wall time (CPULIMIT) has been removed (was 8 hrs/job)
  • Job slots raised to 48, is comprised of
    • greentail our /sancratch provider and redhat 5.5
    • cottontail2 physically identical to greentail for fail over
      • standby scheduler master for cottontail
    • swallowtail secondary login node
    • petaltail, sandbox and Warewolf provisioning node
    • n29 and n31, our OpenHPC test cluster compute nodes, CentOS 7.3
      • joined to our Openlava environment

You can target individual nodes with '#BSUB -m node-name' in your submit script.

DR

  • sharptail2dr is our disaster recovery node (to back up sharptail's /home)
  • Every couple of days users' /home will be refreshed on this DR node
  • 17TB of usable storage
  • Users selected for first or refresh backup are obtained from job submission logs last 30 days
  • No logins are permitted
  • Node will eventually be moved to Freeman DR location
  • If users become inactive, backup home directory will not be removed (while space is available)
  • vlan52 bonded interfaces (2G connection)


Back

cluster/162.txt · Last modified: by hmeij07