GitLab

Conflicts:
	src/lib/Components/system/CraySystem.py

Resolve "Doc Update for Cray Systems"

Closes #32

See merge request !17

Found a bad default path for apbasil.  This is now something that should
work on a default Cray install.

This was data that needed to be added to the manpages for Cray systems.

This should effectively end the startup race condition

This should get rid of the bulk of the 1234567 exit statuses. Forces a
timeout.  The timeout goes away when the job is started.  This should
fix the process group initilization/start gap.
Closes #31

See merge request !16

This should get rid of the bulk of the 1234567 exit statuses. Forces a
timeout.  The timeout goes away when the job is started.  This should
fix the process group initilization/start gap.

Checking in fixes for find queue equivalence classes that impact
draining.  Drain-status-clear now working.  Stub for drain selection.

Fixing nodelist so it shows active reservations

Node list commands should show which nodes have an active reservation
attached to them.  Broke when going over to compact-notation.
Closes #28

See merge request !15

Node list commands should show which nodes have an active reservation
attached to them.  Broke when going over to compact-notation.

Resolve "Nodeadm -l/nodelist fetch is slow"

Closes #29 

Major speedup achieved doing two things:
1) bypass the large amount of recursion in the XMLRPC marshaler by converting the data to send as a json string (this is a flag as to whether or not you want dictionary data in this form)

2) Added a parameter restriction so you can request only specific fields.  Used in nodeadm -l and nodelist to reduce data being sent.

See merge request !14

Mocked up by replicating node data in testing.

Resolve "Reservation-location interaction"

Closes #25 
This resolves a number of issues with _assemble_queue_data with types and methods of reservation avoidance.
It also fixes issues with reservations and --attrs location= being used together

See merge request !13

Make sure that an update cannot change this list midflight for a job.

Caller also holds this lock at this point in time.  The node_lock must
be reentrant!

Thanks Eric!  Duplicated nids are now avoided.

Resolve "Setres Slow"

Closes #27

Now doing a single call to verify_locations instead of one per node requested. 

See merge request !12

Reducing the calls to verify locations should significantly speed up
setres on Cray systems.

Fixes attrs location evading cobalt admin down on nodes.

Non-idle nodes are now fully respected.  Consistiently get string nid
lists out of this.  ValueError doesn't get raised if the attrs location
exists stradling a reservation (still in the queue, but not available
due to the reservation).

Including this until a later upgrade can be done that has Cobalt
directly send a SIGKILL 5 minutes after we try to signal an aprun at
cleanup.

Resolve "FIX: Overly Aggressive Cleanup"

Closes #26

See merge request !11

The apid fetch wasn't restricting itself to the actual ALPS reservation.
This was causing everything to get killed.

System component restart on the fly should be safe again.  We recover
the process groups properly now.  Found this while testing other changes
in the fix for aggressive cleanup.

Fixing a situation where locations when set in a resrvation job causes
issues.

There was one further step needed for running jobs. Also fixing a
potential statefile issue with prior versions.

Nodes brought up in a disabled state at machine boot will not be
reported in ALPS.  This allows us to detect and recover when nodes are
warm-swapped back into service.