You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 12 Next »

Batch Nodes

Depending on your data access you may need to submit jobs to a specific farm. This is accomplished by submitting to the appropriate LSF batch queue. Refer to the table below. Jobs for the running experiment should be submitted to high priority queues psnehq and psfehq. Multi-core OpenMPI jobs should be run in either the psnehmpiq or psfehmpiq batch queue, see the following section on "Submitting OpenMPI Batch Jobs". Simulation jobs should be submitted to the low priority queues psfehidle and psfehidle. CPU intensive jobs which don't demand high data throughout should be submitted to the psanacsq queue.

Experimental Hall

Queue

Nodes

Data

Comments

NEH

psnehq

psana11xx

ana01, ana02

Jobs <= 6 cores

 

psnehmpiq

psana11xx,psana12xx

ana01, ana02

OpenMPI jobs > 6 cores, preemptable

 

psnehidle

psana12xx

 

Simulations, preemptable, low priority

FEH

psfehq

psana13xx

ana11, ana12

Jobs <= 6 cores

 

psfehmpiq

psana13xx,psana14xx

ana11, ana12

OpenMPI jobs > 6 cores, preemptable

 

psfehidle

psana14xx

 

Simulations, preemptable, low priority

NEH/FEH

psanacsq

psanacs0xx

ana01, ana02, ana11, ana12

CPU intensive, limited data throughput

Submitting Batch Jobs

LSF (Load Sharing Facility) is the job scheduler used at SLAC to execute user batch jobs on the various batch farms. LSF commands can be run from a number of SLAC servers, but best to use psexport or pslogin. Login first to pslogin (from SLAC) or to psexport (from anywhere). From there you can submit a job with the following command:

bsub -q psnehq -o <output file name> <job_script_command>

For example:

bsub -q psnehq -o ~/output/job.out my_program

This will submit a job (my_program) to the queue psnehq and write its output to a file named ~/output/job.out. You may check on the status of your jobs using the bjobs command.

Similar command:

bsub -q psfehq -o ~/output/log.out "ls -l"

will execute the command line "ls -l" in the batch queue psfehq and write its output to a file named ~/output/log.out

Resource requirements can be specified using the "-R" option. For example, to make sure that a job is run on a node with 1 GB (or more) of available memory, use the following:

bsub -q psnehq -R "rusagemem=1024" my_program
Submitting OpenMPI Batch Jobs

The RedHat supplied OpenMPI packages are installed on pslogin, psexport and all of the psana batch servers.

The system default has been set to the current version as supplied by RedHat.

$ mpi-selector --query
default:openmpi-1.4-gcc-x86_64
level:system

Your environment should be set up to use this version (unless you have used RedHat's mpi-selector script, or your login scripts, to override the default). You can check to see if your PATH is correct by issuing the commandwhich mpirun. Currently, this should return /usr/lib64/openmpi/1.4-gcc/bin/mpirun. Future updates to the MPI version may change the exact details of this path.

In addition, your LD_LIBRARY_PATH should include /usr/lib64/openmpi/1.4-gcc/lib (or something similar).

For notes on compiling examples, please see:

http://www.slac.stanford.edu/comp/unix/farm/mpi.html 

The following are examples of how to submit OpenMPI jobs to the PCDS psnehmpiq batch queue:

bsub -q psnehmpiq -a mympi -n 32 -o ~/output/%J.out ~/bin/hello

Will submit an OpenMPI job (-a mympi) requesting 32 processors (-n 32) to the psnehmpiq batch queue (-q psnehmpiq).

bsub -q psfehmpiq -a mympi -n 16 -R "span[ptile=1]" -o ~/output/%J.out ~/bin/hello

Will submit an OpenMPI job (-a mympi) requesting 16 processors (-n 16) spanned as one processor per host (-R "span[ptile=1]") to the psfehmpiq batch queue (-q psfehmpiq).

bsub -q psfehmpiq -a mympi -n 12 -R "span[hosts=1]" -o ~/output/%J.out ~/bin/hello

Will submit an OpenMPI job (-a mympi) requesting 12 processors (-n 12) spanned all on one host (-R "span[hosts=1]") to the psfehmpiq batch queue (-q psfehmpiq).

Common LSF Commands

Report status of all jobs (running, pending, finished, etc) submitted by the current user:

bjobs -w -a

Report only running or pending jobs submitted by user "radmer":

bjobs -w -u radmer

Report running or pending jobs for all users in the psnehq queue:

bjobs -w -u all -q psnehq

Kill a specific batch job based on its job ID number, where the "bjobs" command can be used to find the appropriate job ID (note that only batch administrators can kill jobs belonging to other users).

bkill JOB_ID

Report current node usage on the two NEH batch farms:

bhosts -w ps11farm ps12farm

The following links give more detailed LSF usage information:

PowerPoint presentation describing LSF for LCLS users at SLAC

Batch system in a nutshell

Overview of LSF at SLAC

Suspending Idle Queues

Jobs submitted to a high priority queue (eh psnehq) will automatically suspend jobs running on the same hardware, but in the lower priority queues (eg pnehmpiq and psnehidle). This suspension can take from a few seconds to up to a few minutes and when many small high priority jobs are submitted in rapid succession, the time taken to suspend lower priority jobs affects the performance of the high priority jobs. For this reason there is a mechanism to suspend the lower priority queues for any specified high priority queue. The command, which can be issued by LCLS scientists and PCDS people, is:

/reg/g/psdm/qcntrl/psniceq <high-priority-queue> <time>

Examples:

/reg/g/psdm/qcntrl/psniceq psnehq 30     # Suspend idle queues conflicting with psnehq for 30 minutes
/reg/g/psdm/qcntrl/psniceq psfehq 40     # Suspend idle queues conflicting with psfehq for 40 minutes
/reg/g/psdm/qcntrl/psniceq psanacs 8h    # Suspend idle queues conflicting with psanacs for 8 hours
  • No labels