Jump to content
  • Announcements

    • admin

      PBS Forum Has Closed   06/12/17

      The PBS Works Support Forum is no longer active.  For PBS community-oriented questions and support, please join the discussion at http://community.pbspro.org.  Any new security advisories related to commercially-licensed products will be posted in the PBS User Area (https://secure.altair.com/UserArea/). 

bflynt

Members
  • Content count

    2
  • Joined

  • Last visited

  1. $PBS_HOME/mom_priv/config

    On slide 189 of the training manual "Managing and Using PBS Professional" for PBS Pro 12.2 it states a MoM can be configured to kill user-owned processes when that user does not have a job running on that host through PBS. All you have to do is add a parameter to $PBS_HOME/mom_priv/config. This file does not exist for my new installation of PBS Pro 12.2.4. Has the location/name of the file changed? If I create the file new will it be picked up when I send the -SIGINT to the MoMs? Thanks
  2. Queue Chunks/Nodes

    I'm trying to set up my first queue as an admin and have a couple questions related to the chunks & nodes. Machine (SGI IceX & PBS Pro 12.4): Each node has 2 CPU's with 10 physical cores each for a total of 20 physical cores per node. Each core can use hyper-threading (HT) to make a total of 40 cores per node. Scenario: I want to create a queue where a person can only use 1 - 18 nodes. In this way they can use 1 - 360 physical cores or if they are willing to put up with the performance penalty of HT they can use up to 720. Another way of thinking about it would be allowing the user to over/under subscribe as they choose but limit them to 18 nodes? “set queue Name resources_max.ncpus = 360” - Allows 180 cores w/HT OR 360 physical cores “set queue Name resources_max.ncpus = 720” - Allows 360 cores w/HT or 720 physical cores. The only way I see to allow this is to set the max.ncpus = 720 but only allow a maximum chunk of 360/20 = 18 nodes. Is there a way to limit the number of nodes when setting up a queue? Thanks
×