Stack Overflow
Stack Overflow

Questions tagged [pbs]

PBS stands for portable batch system, and describes a family of software products for high performance computing.

PBS stands for portable batch system, and describes a family of software products for high performance computing. The software is a resource manager that is used to manage jobs, including their submission, running, and basic managing. They are often used in UNIX cluster environments and can often be used with schedulers.

Modern PBS daemons are descendants from OpenPBS; two notable descendants are TORQUE and PBSPro. TORQUE is an open source product and is maintained by Adaptive Computing. More information can be found on its wikipedia page. Documentation for TORQUE can be found on Adaptive's website. PBSPro is a commercial product that is developed by Altair Engineering. PBSPro's user guide can be found here.

428 questions
0
votes
1 answer

How can I see the `qsub` command used to submit a job?

I have a job running in a remote cluster. Is there a way to see what qsub command was used (the options and so on) to start the job?
a06e
  • 18,594
  • 33
  • 93
  • 169
0
votes
1 answer

PBS deferred execution with job array

I'm trying to write a job array so that the individual jobs start at slightly different points in time. (Because the program I evoke uses the time of day to the nearest second as a random seed and it will generate identical results if all jobs are…
ahj
  • 15
  • 4
0
votes
1 answer

MPICH stop running across more than one node

I have a MPI fortran application using MPICH that can be launched/run without problem if I use: mpiexec -n 16 -f $PBS_NODEFILE $PBS_O_WORKDIR/myMODEL.a In the above example I am asking 2 nodes, once each node on the cluster has 8 cpu. The…
Quim
  • 161
  • 2
  • 7
0
votes
1 answer

What is causing repeated glibc error with plink/batch job software-?

I am running plink software through a PBS batch job. This error occurs when I run the job: *** glibc detected *** /software/plink: double free or corruption (out): 0x000000018dfafca0 *** ======= Backtrace: ========= [0x7d7691] [0x7d8bea] …
roserose
  • 1
  • 3
0
votes
1 answer

Defining a C++ file/function name in a PBS batch script file

I am batch processing in C++ and want to know whether it is possible to define a .cpp file name in the PBS script file (see below). For example, for one of my .cpp files I have two versions: a parallel OpenMP version (func_parallel.cpp) and a serial…
krylov
  • 79
  • 1
  • 4
0
votes
0 answers

Is it possible to pause a job in a PBS scheduler?

I have jobs running in a supercomputer, when I've submitted a new one it has entered in waiting status (qw). This last job is priority in relation with the ones that are running which I don't want to kill. What I'd like to do is to pause them and…
ziulfer
  • 1,339
  • 5
  • 18
  • 30
0
votes
2 answers

Torque pbs_python submit job error (15025 queue already exists)

I try to execute this example script (https://oss.trac.surfsara.nl/pbs_python/wiki/TorqueUsage/Scripts/Submit) #!/usr/bin/env python import sys sys.path.append('/usr/local/build_pbs/lib/python2.7/site-packages/pbs/') import pbs server_name =…
joeunderwood
  • 3
  • 2
0
votes
0 answers

Hadoop Job via Open PBS

I am using OpenPBS to submit a Hadoop job on cluster. Everything works well when Hadoop job is completed successfully. I am using one master node and one slave node in configuration. When i use qdel to delete Hadoop job the Java processes running…
Gearloose
  • 3
  • 2
0
votes
0 answers

View GNUPLOT figures from cluster backend

I'm currently trying to run some quick diagnostic tests on some parallel code. I'm submitting the code through a batch system to the cluster backend through .pbs scripts. I'm capturing the diagnostic data from the executables but I would like to…
oLas
  • 1,171
  • 1
  • 9
  • 17
0
votes
1 answer

Can we use a specific algorithm to a particular queue in PBS

I would like to use a specific algorithm to a particular queue. Is it possible?
Alvin
  • 940
  • 2
  • 13
  • 27
0
votes
0 answers

PBS job array id placeholder in submit

I was searching around the web for an answer to this question however I couldn't find anything useful, so I've got the feeling what I'm looking for is not possible but maybe I missed something... So I'm just gonna try to ask here: When submitting…
steve
  • 133
  • 1
  • 2
  • 10
0
votes
0 answers

Supend/Resume Thread, Specificly execution on code by the procressor Linux

I'm working on a program that may be run under PBS with a specific CPU count, less than the total number of CPU's. I have previously that PBS enforces this limited by terminating the program if it exceeds the limit. My program will use threads,…
Glen Fletcher
  • 644
  • 5
  • 21
0
votes
1 answer

How to create a job script to automatise this?

Right now I am doing the following on a cluster: (i) qsub-X -I -l walltime=60:00:00,nodes=1:ppn=8 (ii) submitting myjob (using ./myjob) which has the following contents #!/bin/bash i=1 nohup ./a.out $i 2 42 & nohup ./a.out $i 43 60 & nohup ./a.out…
Gravity Boy
  • 3
  • 3
0
votes
2 answers

Find free nodes on cluster with SGE

I'm looking for the SGE equivalent to PBS's "qstat -freenodes", basically I want to find all nodes that have nothing running. Suggestions?
user2796649
  • 1
  • 1
  • 1
0
votes
2 answers

How to redirect qsub output into a text file

In my code I want to use the qsub output information such as job ID, node name etc., so I'm think about redirecting the qsub output into some file at the time when the node is allocated, which then can be later used by my code. For example, when I…
xslittlegrass
  • 4,826
  • 4
  • 26
  • 32
1 2 3
…
28 29