(Click to open topic with navigation)

Appendices > Appendix W: Moab RM Language (WIKI) Interface > Managing Resources with SLURM

Conventions

W.2 Managing Resources with SLURM

This section demonstrates how Moab uses the Moab RM language (formerly called WIKI) to communicate with SLURM. For SLURM configuration instructions, see the Moab-SLURM Integration Guide.

W.2.1 Commands

All commands are requested via a socket interface, one command per socket connection. All fields and values are specified in ASCII text.

Supported Commands are:

W.2.1.1 Moab RM Language Query Resources

W.2.1.1.1 Moab RM Language Query Resources Request Format

CMD=GETNODES ARG={<UPDATETIME>:<NODEID>[:<NODEID>]... | <UPDATETIME>:ALL}

Only nodes updated more recently than <UPDATETIME> will be returned where <UPDATETIME> is specified as the epoch time of interest. Setting <UPDATETIME> to 0 will return information for all nodes. Specify a colon delimited list of NODEIDs if specific nodes are desired or use the keyword ALL to receive information for all nodes.

W.2.1.1.2 Moab RM Language Resources Response Format

The query resources response format is one or more line of the following format (separated with a new line):

<NODEID><ATTR>=<VALUE>[;<ATTR>=<VALUE>]...

<ATTR> is one of the names in the table below and the format of <VALUE> is dependent on <ATTR>.

Example 25-4: Moab RM language resource query and response

Request:

CMD=GETNODES ARG=0:node001:node002:node003

Response:

node001 UPDATETIME=963004212;STATE=Busy;OS=AIX43;ARCH=RS6000...
node002 UPDATETIME=963004213;STATE=Busy;OS=AIX43;ARCH=RS6000...
...

W.2.1.2 Moab RM Language Query Workload

W.2.1.2.1 Moab RM Language Query Workload Request Format

CMD=GETJOBS ARG={<UPDATETIME>:<JOBID>[:<JOBID>]... | <UPDATETIME>:ALL }

Only jobs updated more recently than <UPDATETIME> will be returned where <UPDATETIME> is specified as the epoch time of interest. Setting <UPDATETIME> to 0 will return information for all jobs. Specify a colon delimited list of JOBID's if information for specific jobs is desired or use the keyword ALL to receive information about all jobs.

W.2.1.2.2 Moab RM Language Query Workload Response Format

SC=<STATUSCODE> ARG=<JOBCOUNT>#<JOBID>:<FIELD>=<VALUE>;[<FIELD>=<VALUE>;]...[#<JOBID>:<FIELD>=<VALUE>;[<FIELD>=<VALUE>;]...]...

or

SC=<STATUSCODE> RESPONSE=<RESPONSE>

FIELD is either the text name listed below or A<FIELDNUM>
(i.e. UPDATETIME or A2)

STATUSCODE values:

RESPONSE is a statuscode sensitive message describing error or state details.

W.2.1.2.3 Moab RM Language Query Workload Example

Request:

CMD=GETJOBS ARG=0:ALL

Response:

ARG=2#nebo3001.0:UPDATETIME=9780000320;STATE=Idle;WCLIMIT=3600;...

W.2.1.3 StartJob

The StartJob command may only be applied to jobs in the Idle state. It causes the job to begin running using the resources listed in the NodeID list.

send CMD=STARTJOB ARG=<JOBID> TASKLIST=<NODEID>[:<NODEID>]...

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message possibly further describing an error or state

Example 25-5: Job start

# Start job nebo.1 on nodes cluster001 and cluster002

# send 
CMD=STARTJOB ARG=nebo.1 TASKLIST=cluster001:cluster002
# receive 
SC=0;RESPONSE=job nebo.1 started with 2 tasks

W.2.1.4 CancelJob

The CancelJob command, if applied to an active job, will terminate its execution. If applied to an idle or active job, the CancelJob command will change the job's state to Canceled.

send CMD=CANCELJOB ARG=<JOBID> TYPE=<CANCELTYPE>

<CANCELTYPE> is one of the following:

ADMIN (command initiated by scheduler administrator)
WALLCLOCK (command initiated by scheduler because job exceeded its specified wallclock limit)

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message further describing an error or state

Example 25-6: Job cancel

# Cancel job nebo.2

# send 
CMD=CANCELJOB ARG=nebo.2 TYPE=ADMIN'
# receive 
SC=0 RESPONSE=job nebo.2 canceled

W.2.1.5 SuspendJob

The SuspendJob command can only be issued against a job in the state Running. This command suspends job execution and results in the job changing to the Suspended state.

send CMD=SUSPENDJOB ARG=<JOBID>

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message possibly further describing an error or state

Example 25-7: Job suspend

# Suspend job nebo.3

# send 
CMD=SUSPENDJOB ARG=nebo.3
# receive 
SC=0 RESPONSE=job nebo.3 suspended

W.2.1.6 ResumeJob

The ResumeJob command can only be issued against a job in the state Suspended. This command resumes a suspended job returning it to the Running state.

send CMD=RESUMEJOB ARG=<JOBID>

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message further describing an error or state

Example 25-8: Job resume

# Resume job nebo.3

# send 
CMD=RESUMEJOB ARG=nebo.3
# receive 
SC=0 RESPONSE=job nebo.3 resumed

W.2.1.7 RequeueJob

The RequeueJob command can only be issued against an active job in the state Starting or Running. This command requeues the job, stopping execution and returning the job to an idle state in the queue. The requeued job will be eligible for execution the next time resources are available.

send CMD=REQUEUEJOB ARG=<JOBID>

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message further describing an error or state

Example 25-9: job requeue

# Requeue job nebo.3

# send 
CMD=REQUEUEJOB ARG=nebo.3
# receive 
SC=0 RESPONSE=job nebo.3 requeued

W.2.1.8 SignalJob

The SignalJob command can only be issued against an active job in the state Starting or Running. This command signals the job, sending the specified signal to the master process. The signaled job will be remain in the same state it was before the signal was issued.

send CMD=SIGNALJOB ARG=<JOBID> ACTION=signal VALUE=<SIGNAL>

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message further describing an error or state

Example 25-10: Job signal

# Signal job nebo.3

# send 
CMD=SIGNALJOB ARG=nebo.3 ACTION=signal VALUE=13
# receive 
SC=0 RESPONSE=job nebo.3 signalled

W.2.1.9 ModifyJob

The ModifyJob command can be issued against any active or queued job. This command modifies specified attributes of the job.

send CMD=MODIFYJOB ARG=<JOBID> [BANK=name] [NODES=num] [PARTITION=name] [TIMELIMIT=minutes]

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message further describing an error or state

Example 25-11: Job modify

# Signal job nebo.3

# send 
CMD=MODIFYJOB ARG=nebo.3 TIMELIMIT=9600
# receive 
SC=0 RESPONSE=job nebo.3 modified

W.2.1.10 JobAddTask

The JobAddTask command allocates additional tasks to an active job.

send CMD=JOBADDTASK ARG=<JOBID> <NODEID> [<NODEID>]...

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message possibly further describing an error or state

Example 25-12: Job addtask

# Add 3 default tasks to job nebo30023.0 using resources located on nodes cluster002, cluster016, and cluster112.

# send 
CMD=JOBADDTASK ARG=nebo30023.0 DEFAULT cluster002 cluster016 cluster112
# receive 
SC=0 RESPONSE=3 tasks added

W.2.1.11 JobRemoveTask

The JobRemoveTask command removes tasks from an active job.

send CMD=JOBREMOVETASK ARG=<JOBID> <TASKID> [<TASKID>]...

receive SC=<STATUSCODE> RESPONSE=<RESPONSE>

STATUSCODE >= 0 indicates SUCCESS
STATUSCODE < 0 indicates FAILURE
RESPONSE is a text message further describing an error or state

Example 25-13: Job removetask

# Free resources allocated to tasks 14, 15, and 16 of job nebo30023.0

# send 
CMD=JOBREMOVETASK ARG=nebo30023.0 14 15 16
# receive 
SC=0 RESPONSE=3 tasks removed

W.2.2 Rejection Codes

Related topics