To determine why a particular job will not start, there are several commands which can be helpful.

checkjob -v

    Checkjob will  evaluate the ability of a job to start immediately.  Tests include resource access, node state, job constraints (ie, startdate, taskspernode, QOS, etc).  Additionally, command line flags may be specified to provide further information.

  -l <POLICYLEVEL>    // evaluate impact of throttling policies on job feasibility
  -n <NODENAME>       // evaluate resource access on specific node
  -r <RESERVATION_LIST>  // evaluate access to specified reservations

checknode

    Display detailed status of node

diagnose -j

    Display high level summary of job attributes and perform sanity check on job attributes/state.

diagnose -q

    Display various reasons job is considered 'blocked' or 'non-queued'.

showbf -v

    Determine general resource availability subject to specified constraints.

See also:

   Diagnosing System Behavior/Problems