Versions Compared

    Old Version 8

    changes.mady.by.user Unknown User (joshua)

    Saved on

    compared with

    New Version 9

    changes.mady.by.user John Burk

    Saved on

    Key

    • This line was added.
    • This line was removed.
    • Formatting was changed.
    Comment: Published by Scroll Versions from this space and version 6.7-2

    ...

    • The instances that were automatically expanded by SmartShare ("secondary instances") run at low priority, and are the first subject to pre-emption in order to run primary instances from other jobs. Secondary instances may also be pre-empted in order to run secondary instances from other jobs, to balance the number of secondary instances among all jobs.  
    • The method of pre-emption can either be "aggressive", meaning the instance is immediately terminated, or "passive", meaning the instance is allowed to finish processing the current agenda item before terminating, and is configured by the site administrator (see supervisor_smart_share_preempt_policy below).
    • The default smart share pre-emption mode is "aggressive"; secondary instances will be stopped immediately in order to accomplish the balancing of jobs as quickly as possible

    Anchor
    configuration
    configuration
    Excerpt

    Configuring SmartShare

    Tip

    SmartShare is automatically enabled for new 6.6+ installs and upgrades alike.

    To opt out, the site administrator can set the supervisor_smart_share_mode and supervisor_smart_share_preempt_policy in qb.conf on the Supervisor machine:

    supervisor_smart_share_mode = none

    supervisor_smart_share_preempt_policy = disabled

    • supervisor_smart_share_mode
      • Can be either “jobs” or “none”.  
      • default: "jobs"
      • Setting it to “jobs” will make the system try to balance the number of the automatically-expanded “secondary" instances on a job-to-job basis
      • Setting it to “none” disables SmartShare. 
    • supervisor_smart_share_preempt_policy
      • method of preemption for secondary instances 
      • aggressive, passive, disabled
      • default: aggressive
    • supervisor_default_max_cpus
      • used to set the site-wide default value of “max_cpus” if not given at submission
      • default: -1
      • Note: “*” can be used in the qb.conf file too, instead of -1
    • supervisor_max_cpus_limit
      • largest value of “max_cpus” that can be used on any job
      • default 100
      • Note: if any job specifies a value greater than this, the system will silently cap it to this value