wiki.chpc.ac.za

User Tools

Site Tools

You are here: start » quick » pbspro
Trace: • pbspro
quick:pbspro

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
quick:pbspro [2014/01/07 13:00]
andyr 		quick:pbspro [2025/09/22 17:47] (current)
kevin [Example 4 : empty job]
Line 1: Line 1:
 ====== Job submission using PBSPro ====== ====== Job submission using PBSPro ======
  
-As of January 2014, CHPC has a new scheduler - PBSPro.+The CHPC system uses the PBSPro scheduler.
  
-Main user documentation can be found at http://resources.altair.com/pbs/documentation/support/PBSProUserGuide12.1.pdf+Main user documentation can be found at [[https://www.altair.com/pbs-works-documentation/|Altair]]
  
 But here is a summary of how to submit jobs at CHPC. But here is a summary of how to submit jobs at CHPC.
Line 12: Line 12:
   *     ''qstat'' see all jobs and their status   *     ''qstat'' see all jobs and their status
   *     ''qdel'' delete a job   *     ''qdel'' delete a job
-  *     ''qalter'' modify options on a pending job +  *     ''qalter'' modify options on a pending job           
 +  * ''qsig'' send a signal to a job (eg. to terminate it)  
  
  
 ====How to submit a batch job==== ====How to submit a batch job====
  
-Use the qsub command to submit a script file. PBSPro job file allows for specification of options at the beginning of the file prefaced by the #PBS delimiter followed by PBS commands. Commands will be executed in the order given in the script.+Use the ''qsub'' command to submit a script file to the scheduler. PBS-Pro jobs can be controlled using command line switches, //or// directives in the job submission file prefaced by the ''#PBS'' keyword. 
  
-A script can include just about anything which you could do during a terminal session such as set environment variables, change directories, and move files. See the qsub man page for a complete list of options.+See the ''qsub'' man page for a complete list of options. 
  
-''qsub myscriptname''+The first line of a script file may specify the interpreter, eg., bash is selected by using ''#!/bin/bash'' as the first line of the job script file.
  
-=== Example PBS scripts ===+A script can include just about anything which you could do during a terminal session such as set environment variables, change directories, and move files. 
  
-On a cluster system, run an executable on 3 nodes using all 8 cores per node with 8 MPI processes for 5 hours+> Job script files can be named to anything allowed for a regular file, but it is strongly recommended that you use ''.pbs'' as the file extension to make it easy to distinguish job scripts from other shell scripts (''.sh'').
  
-<code> 
-#!/bin/sh 
-#PBS -j oe 
-#PBS -l walltime=5:00:00 
-#PBS -l select=3:ncpus=8:mpiprocs=8 
-#PBS -V 
-cd ${PBS_O_WORKDIR} 
-</code> 
  
-On a non-cluster system, run an executable on 24 cores for 5 hours+====How to start an interactive job on a compute node====
  
-<code> +''qsub -I -V''
-#!/bin/sh +
-#PBS -j oe +
-#PBS -l walltime=5:00:00 +
-#PBS -l ncpus=24 +
-#PBS -V +
-cd ${PBS_O_WORKDIR} +
-</code>+
  
-===How long can a job run===+to start an interactive session, retaining all environment variables.
  
-There is no limit to the amount of time that a PBS job can run. If no time limit is specified, a default of 12 hours is assigned. Remember to check point long running jobs. 
  
-To specify a time, include the following line in the submission script:+====How to monitor job submissions to the queue====
  
-''#PBS -l walltime=hhhh:mm:ss''+The job number will be returned if the job has been accepted by the scheduler. Use this 
 +number to check on the progress of a specific job:
  
-===Exclusive use of cluster nodes===+''qstat -f <jobnum>''
  
-On cluster systems, if a job does not request all the cores on a node, it is possible another job will share the same node. To prevent this, request exclusive use.+To inspect jobs that have already finished:
  
-''#PBS -l place=excl''+''qstat -x -f <jobnum>''
  
-===How to export interactive session environment to job===+or
  
-To include the shell environment in the batch job, either use the -V option with qsub or as a PBS directive+''qstat -xf <jobnum>''
  
-''qsub -V'' +====How to monitor job arrays====
-         +
-''#PBS -V''+
  
-===Hyper-Threading===+To see the array job status on the queue, postfix the 
 +jobnumber with empty square brackets:
  
-On cluster systems with Hyper-Threading, the Hyper-Threading is enabled by default. This allows users to run two tasks or threads per core instead of just one. Users can set npcus and mpiprocs to 16 even though there are only 8 physical cores on each node.+''qstat -J <jobnum>[]''
  
-''#PBS -l select=2:npcus=16:mpiprocs=16'' 
  
-However, if users specify only 8 ncpus and mpiprocs per node.+To look at one specific job in the array, add ''-t'' to the qstat arguments:
  
-''#PBS -l select=2:ncpus=8:mpiprocs=8''+''qstat -xft <jobnum>[array-index]''
  
-then all 16 tasks (or threads), in this example, are placed on a single 8 core node, while the second node will be empty. This will result in your code running at about half the speed you anticipated. 
  
-To avoid this pitfall, use "place=scatter" or "place=scatter:excl" and 8 tasks will be placed on the first node and 8 on the second node.+eg
  
-''#PBS -l select=2:npcpus=8:mpiprocs=8,place=scatter:excl''+''qstat -xft 967890[2]''
  
-For more on Hyper-Threading, see Intel's Hyper-Threading Technology 
  
-See the qsub man page for a complete list of options 
  
-===Suppose I want to do a parameter study. How do I submit all these jobs with a different value of parameter?===+=====PBS-Pro Job Exit Codes =====
  
-Use PBS Job Arrays. You can specify how many jobs to run by adding the directive+====Job Exit Codes Between 0 and 128 (or 256)==== 
 +This is the exit value of the top process in the job, typically the shell. This may be the exit value of the last command executed in the shell or the .logout script if the user has such a script (csh).
  
-#PBS -J <range>+====Job Exit Codes >= 128 (or 256)==== 
 +This means the job was killed by the PBS scheduler by sending it a signal. 
  
-where range is X-Y:Z. So 1-10:2 indicates all the even jobs from 1 to 10, i.e., 2,4,6,8 and 10.+The **modulo** or **remainder** operator [[http://en.wikipedia.org/wiki/Modulo_operation]] is used to interpret (or “decode”) PBS job exit values. 
  
-PBS defines two environment variables: 
  
-PBS_ARRAY_INDEX     job array index +The signal is given by X modulo 128 (or 256). An exit value of 137 means the job's top process was killed with signal 9 because ''137 mod 128 = 9''. 
-PBS_ARRAY_ID        job array id+
  
-These variables are also defined as attributes:+Depending on the system, a value greater than 128 or 256, see ''man wait(2)'', is the signal that was sent by PBS-Pro to kill the job. (i.e., 265 mod 256 = 9 or 271 mod 256 = 15.) 
  
-array_index +Exit code 271 means that the job exceeded the limit requested at submission, eg. walltime or cpu usage, and was killed.
-array_id+
  
-Based on the job array index, different input files can be used for each job in the job array. Below is a job script example that submits two jobs, each using one processor.+See ''man kill'' for a mapping of signal numbers to signal name on your operating system. 
 +====Terminate a job by signal==== 
 +Send a signal to the job
  
-NOTE: The PBS directives specify the resources that will be used by EACH individual job, NOT all the jobs together.+'' qsig -s SIGTERM  <jobnum>  ''
  
-<code> 
-#!/bin/sh 
-#PBS -V 
-#PBS -l select=1:ncpus=1:mpiprocs=1,walltime=48:00 
-#PBS -N Job_Array_Test 
-#PBS -j oe -o ja.^array_index^.pbs 
-#PBS -J 1-2 
-cd $PBS_O_WORKDIR 
-# 
-unset echo 
-              
-echo $PBS_ARRAY_INDEX 
-                
-echo $PBS_ARRAY_ID $PBS_ARRAY_INDEX >> ja.$PBS_ARRAY_INDEX.out 
-echo ' '        >> ja.$PBS_ARRAY_INDEX.out 
-bin/pi < pi.inp >> ja.$PBS_ARRAY_INDEX.out 
-                 
-exit 
-</code> 
  
-===How do I determine the number of cores I have requested in my job script?===+===== Examples: PBS-Pro job submission scripts =====
  
-To determine the number of cores requested, include the following line in the submission script:+[[howto:PBS-Pro_job_submission_examples]]
  
-''set NCORES = `cat $PBS_NODEFILE | wc -l`''+===== Examples: Gaussian jobs =====
  
-===How do I determine the number of nodes I have requested in my job script?=== 
  
-To determine the number of nodes requested, include the following line in the submission script:+[[howto:gaussian|Gaussian Single and Multi-Node Scripts]] 
 +    
 +   
  
-''set NNODES  = `cat $PBS_NODEFILE | uniq | wc -l `'' 
  
-===A job submitted to the queue is not running=== 
  
-Look at the job status with qstat. The next to last line of the output is a comment describing the job status. Possible outputs include: 
  
-''qstat -f yourjobid'' 
  
-  *  Job run at date at time on hostname +===== Examples: Amber jobs =====
-        Job is running OK +
  
-  *  Not Running: No available resources on nodes 
-        Job requires more memory,cores, or processors than currently available, or you have requested more resources than what physically exists on the system.  
  
-  *  Job held, too many failed attempts to run +[[howto:amber|Amber job submission scripts]]
-        Delete and resubmit job+
  
-If this persists, contact User support  
  
-  *  Not Running, Draining system to allow starving job to run 
-        Job will not run because the resources are reserved for other jobs.  
  
-===Queued Jobs stuck in an error state (E)===+===== Example: Quantum Espresso =====
  
-Try deleting the job with qdel 
  
-''qdel -Wforce yourjobid''+[[howto:quantum_espresso|Quantum Espresso]]
  
-The following must be **plain text** files, as created by unix programs like ''nano'' or ''vi''. If you wish to create them on your desktop and copy them over, ensure they contain no formatting and have unix line endings. Microsoft Word would be a bad choice. 
  
-===== Example 1 : Gaussian job ===== +===== Example 4 : empty job =====
-<code> +
-#PBS -N eric.job +
-#PBS -l select=8:ncpus=1:jobtype=dell,place=free:group=nodetype +
-#PBS -l select=1: +
-#PBS -l walltime=1:00:00 +
-#PBS -q workq +
-#PBS -m be +
-#PBS -o /export/home/embele/scratch5/eric.out +
-#PBS -e /export/home/embele/scratch5/eric.err +
-#PBS +
- +
-cd $PBS_O_WORKDIR +
-source /etc/profile.d/modules.sh +
-module add gaussian/g09.D01 +
-g09 < eric.com > sibusiso.log +
-</code> +
- +
-===== Example 2 :  Amber job ===== +
- +
-<code> +
-#PBS -N eric.job +
-#PBS -l select=1:mpiprocs=8 +
-#PBS -l walltime=1:00:00 +
-#PBS -q kepla_k20 +
-#PBS -m be +
-#PBS -o /export/home/embele/amber/amber12/Amber_GPU_Benchmark_Suite/GB/myoglobin/eric.out +
-#PBS -e /export/home/embele/amber/amber12/Amber_GPU_Benchmark_Suite/GB/myoglobin/eric.err +
-#PBS +
-cd $PBS_O_WORKDIR +
-exe=/export/home/embele/amber/amber12/bin/pmemd.MPI +
-###exe=/export/home/embele/amber/amber12/bin/pmemd.cuda.MPI +
-source /etc/profile.d/modules.sh +
-module add intel-XE/c8000 cuda/5.0-c8000 mvapich2/c8000 amber/k20 +
-module add intel-XE/c8000 cuda/5.0-c8000 mvapich2/c8000 amber/k20 +
-nproc=`cat $PBS_NODEFILE|wc -l` +
-time mpirun -np $nproc -machinefile $PBS_NODEFILE $exe -O -i mdin -o mdout -p prmtop -c inpcrd +
-</code> +
- +
-===== Example 3 :  empty job =====+
  
 <code> <code>
 +#! /bin/sh
 #PBS -N <jobname> #PBS -N <jobname>
-#PBS -l select=<totalcores>:ncpus=1:select=<hosts>:jobtype=<architecture>:place=free:group=nodetype+#PBS -l select=<numberofnodes>:ncpus=<totalcores>:jobtype=<architecture>:place=free:group=nodetype
 #PBS -l walltime=<hours>:<minutes>:<seconds> #PBS -l walltime=<hours>:<minutes>:<seconds>
 #PBS -q <queue> #PBS -q <queue>
Line 220: Line 133:
 #PBS -o <path to your output file> #PBS -o <path to your output file>
 #PBS -e <path to your error file> #PBS -e <path to your error file>
-Where +source /etc/profile.d/modules.sh   # so module command works 
-<jobname> = name of the job +cd $PBS_O_WORKDIR   # change to working directory 
-<totalcores>= total number of cores + 
-<hosts> = number of hosts +#Where 
-<architecture> = architecture where the jobs will run (nehalem|westmere|dell) +#<jobname> = name of the job 
-<queue> = submission queue ( workq , priorityq , specialq , intel_mic , spark , kepla_k20 , accelrys)+#<totalcores>= total number of cores 
 +#<hosts> = number of hosts 
 +#<architecture> = architecture where the jobs will run (nehalem, westmere, dell) 
 +#<queue> = submission queue ( serial, smp, normal, ...,  accelrys) 
 +#<executable> = Binary to be run 
 + 
 +mpirun -np <totalcores> <executable>
  
 </code> </code>
  
-//Note that the M9000 sparc queue is called 'spark'// 
  
-===== MPI example =====+ 
 +===== Example 5 : MPI example =====
  
 Syntax Syntax
Line 241: Line 160:
 ... ...
 </code> </code>
- +===== Further examples ===== 
-For more information on qsub +  * Various [[howto:bioinformatics?&#basic_examples|bioinformatics examples]] illustrate some further possibilities. Specifically the blast examples illustrate job arrays and job dependencies. 
-  $ man qsub +  * This [[howto:gpu_gromacs#pbs_job_script|gromacs example]] shows an interesting case where mpi, openmp and the gpus are used in a single job.
- +
-Additional information on the job queues available  +
-  $ qstat -q +
- +
-A minimal script Dell example would be  +
-  $ more mpirun_basic_example +
-  #PBS -l select=2:ncpus=12:mpiprocs=12:jobtype=dell +
-  cat $PBS_NODEFILE +
- +
- +
-submiting the script +
-  $ qsub mpirun_basic_example +
-The submitted jobs output file should produce output similar to  +
-  cnode-6-33 +
-  ... repeated 11 times ... +
-  cnode-6-34 +
-  ... repeated 11 times ... +
/app/dokuwiki/data/attic/quick/pbspro.1389092450.txt.gz · Last modified: 2021/12/09 16:42 (external edit)

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Noncommercial-Share Alike 3.0 Unported
CC Attribution-Noncommercial-Share Alike 3.0 Unported Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki