database.

Jobs are not backfilled due to the fact that backfill does not finish the complete backlog of jobs in the queue before it's interrupted and starts all over again. We sometimes have lots of jobs in the queue of various sizes and users and even with idle nodes short job will not start because of this.  I have made a patch for backfill with a configuration option (bf_continue) to let backfill continue.

Conflicts:
	src/slurmctld/reservation.c

The original reservation data structure is deleted and it's backup
added to the reservation list, but jobs can retain a pointer to the
original (now invalid) reservation data structure.
Bug 250

Conflicts:
	src/slurmctld/node_mgr.c

able to be canceled.  In older versions of freeimpi some of the calls
(ipmi_monitoring_sensor_readings_by_record_id) could hang if it doesn't
work correctly and the timeout mech appears to cause memory corruption.

The code now handles this and does the right thing.

energy data.

Without this fix, jobs that should be initiated by the backfill
scheduler based upon the preemption of other jobs will not be
started.

Signed-off-by: Danny Auble <da@schedmd.com>

the DBD.

Signed-off-by: Danny Auble <da@schedmd.com>

Needed for job arrays to confirm numbers at submit time before we
begin creating the job records

they are missing and on a sub midplane system.

cnode does not have a job running on it do not resume the block.

SoftwareFailure state.

Select/cons_res - If the job request specified --ntasks-per-socket and the
allocation using is cores, then pack the tasks onto the sockets up to the
specified value. Previously it would ignore the ntasks-per-socket
parameter and distribute tasks across sockets