When the optional max_time is not specified for --switches=count, the site
max (SchedulerParameters=max_switch_wait=seconds) is used for the job.
Based on patch from Rod Schultz.

Fix bug in --switch option with topology resulting in bad switch count use.
Patch from Alejandro Lucero Palau (Barcelona Supercomputer Center).

This was due to a bug in select/cons_res with some configuration
optiions and job options, especially if there is more than one
thread per core and the job option includes "--threads-per-core=1".
Fixes problem reported by CSCS.

Added gres_cpus test. Without this test it could lead to the error "fatal: cons_res: sync loop not progressing" With this patch a job will be rejected if asking for unavailable configuration.

Many cosmetic modifications to eliminate warning message from GCC version
4.6 compiler, mostly due to unused variables.

Add the ability for a user to limit the number of leaf switches in a job's
allocation using the --switch option of salloc, sbatch and srun. There is
also a new SchedulerParameters value of max_switch_wait, which a SLURM
administrator can used to set a maximum job delay and prevent a user job
from blocking lower priority jobs for too long. Based on work by Rod
Schultz, Bull.

    --cpus-per-task option. Patch from Martin Perry, Bull.

    scheduling which prevented some jobs from starting as soon as possible.

printed if memory is not allocated.

-- Removed remnant code for enforcing max sockets/cores/threads in the
   cons_res plugin.  This was responsible for a bug reported by Rod Schultz.

    SelectTypeParameters=CR_ONE_TASK_PER_CORE.

    CEA.

    CPUs on some nodes. Patch from Hongjia Cao, NUDT.

value of cpus-per-task into account

    job specifies it's memory requirement, then more CPUs than requested will
    automatically be allocated to a job to honor the MaxMemPerCPU parameter.

  rather than debug3() for most logging 

    and --ntasks-per-node options and the node has fewer CPUs than the count
    specified by --ntasks-per-node.
The bug would prevent test1.37 from completing if the node had fewer than 2 CPUs
    and select/cons_res was used

    minimize system fragmentation.

  for logging purposes. no real change in logic

  internal consistency of select/cons_res data structures if the node
  count of a system changes

cpu count array have one element per node

the test for how many resources are available for pending jobs. changes to the select 
plugins still in progress

    sockets_per_node, min_cores to cores_per_socket, and min_threads to
    threads_per_core (the values are not minimum, but represent the target
    values).