Questions tagged [torque]
TORQUE is a fork of OpenPBS, a job scheduling application used to distribute workloads within a UNIX-based computing cluster.
29
questions
0
votes
0answers
38 views
How do I tell which PBS distribution I have?
I am trying to detect which distribution of PBS is installed on my cluster - Torque/PBS-Pro/OpenPBS etc. According to this thread, I've tried:
$ pbs-config --version
-bash: pbs-config: command not ...
0
votes
1answer
54 views
Less CPUload with torque
We have installed torque on a dual Xeon (26 core, 52 available in hyperthreading). The node is configured with np=104. If I launch a MPI calculation in command line, I get near 100% cpu usage :
%Cpu(...
0
votes
1answer
58 views
Solution for dynamic allocation of CPU cores for MPI program
I am using a MPI program on limited CPU resources. It involved running an application that requires 20 separate processes on a 12 thread CPU. I run it again and again with different parameters.
...
1
vote
1answer
170 views
Running tensorflow code in torque job
I have a cluster running with torque to distribute jobs. I want to run a job with tensorflow code and I am having problems with tensorflow not being recognized.
I installed tensorflow on my LDAP user ...
0
votes
1answer
453 views
How to append PBS job output to log files instead of overwriting it?
I'm using Torque and I want my PBS log+error output to be appended to previous log/error file instead of overwriting it.
0
votes
1answer
44 views
Library not found only when application is executed from PBS file.
I have a compiled file a.out that runs fine when executed directly from my terminal. However, trying to execute that file from my PBS file yields a missing library libmkl_intel_lp64.so. I have already ...
2
votes
1answer
703 views
Job submitted to Torque does not generate error/log file
As stated, I have just installed Torque on a Ubuntu 16.04 machine. The submitted jobs complete just fine but the -e and -o flags seem to not be working. No error and log files are created even though ...
1
vote
0answers
361 views
How to setup bash environment inside Torque PBS? Why source ~/.bashrc doesn't work?
I have successfully installed Torque PBS on my ubuntu server. Job submission is fine. However there is an annoying thing. I found bash environment is not right inside PBS
for example
echo 'echo $...
1
vote
0answers
348 views
PBS Torque Limit Resource by Time of Day
I am using Torque to manage software that I have a limited number of licenses of (4 to be exact). During the day I need to keep 2 licenses free for use of setting up cases and at night and over the ...
2
votes
0answers
72 views
Torque pbs queue system runs queue in reverse
I have a small compute cluster set up on Redhat 7.1.
It runs the PBS torque queue system with version 5.1.1.
When I queue several jobs it starts to run the jobs in "backwards" priority. It starts ...
1
vote
0answers
97 views
Torque queue issue
I am having troubles with Torque + Maui.
The problem is the following:
I have 2 queues, each queue has 10 associated nodes.
If i submit 10k jobs to the first queue and i submit 1 job to the second ...
-1
votes
1answer
1k views
How can we configure torque with multiple nodes for a workstation? [closed]
I've got a GPU workstation with 48 core CPU + 4 NVIDIA GPU. I am going to make this machine to be a small cluster which contains:
4 nodes
12 core +1 CPU/node
I've installed Torque in this machine ...
0
votes
1answer
559 views
prevent normal users from running code on a cluster outside of pbs system
In our cluster with PBS batch system (torque) installed, we wish all the users execute their jobs by qsub so that the CPU resources can be well managed. However, it is found that users in our cluster ...
0
votes
1answer
2k views
Torque reports error when posting job to client nodes
The system has two machines, one (called macondo02) runs pbs_server and pbs_schedule, another (called macondo01) runs pbs_mom. I have ensured that the host can clearly identify the existance of the ...
2
votes
0answers
247 views
Email notifications per JOB ARRAY not per job in PBS torque
Is there a way to configure torque to send email notifications on start and end of job array, and not per job, Im managing job arrays of thousands of jobs, and I dont want to get flooded by mails. But ...
1
vote
1answer
1k views
Why does qdel comman return 'Unknown Job Id'
OS Version:
CentOS release 4.6 (Final) Kernel \r on an \m 2.6.9-100.ELsmp
Problem
When I run qdel i get the following error:
qdel: Unknown Job Id 20432.scyld.localdomain
Information
Output of ...
1
vote
5answers
9k views
I get the error qsub: Bad UID for job execution when trying to submit a job via PBS
OS Version:
CentOS release 4.6 (Final)
Kernel \r on an \m
2.6.9-100.ELsmp
When I attempt to run a job it gives me the error as follows.
qsub: Bad UID for job execution
I have created a fresh user ...
-1
votes
1answer
116 views
Torque: How lock node cores to one application [closed]
I am having an issue that I do not know how to solve. Say I have 2 nodes (node1 and node2) each with 24 cores, I have software where I have a license for 32 cores. I want to be able to configure ...
1
vote
0answers
747 views
Set total memory limit with Torque
I run a moderately sized cluster and I am having a queue problem. For example I have a node with 128GB of memory and a program that I set the amount of memory per core. So for example if I set memory ...
5
votes
0answers
6k views
torque pbs 4.0.1 job stays queued ('Q') state; the scheduler seems not receiving any notification
I am using torque 4.0.1 on openSUSE 12.1 in a cluster environment. When I qsub a job (simple as "echo hello"), it remains in 'Q' state, and never gets scheduled. I can force the job to run with qrun, ...
2
votes
1answer
125 views
qsub: How can I find out what DRM middleware exactly is installed on a cluster?
I have a user account on a very big cluster. I have previous experience with Grid Engine and want to use the cluster for array jobs.
The documentation tells me to use "qsub" for load balancing / ...
1
vote
1answer
2k views
Torque and maui node status
I am new for torque and maui.
I was checking for node state to looking for which nodes are free and which nodes are in use.
For torque one command is pbsnodes. Which gives status and other info ...
1
vote
1answer
844 views
Non-exclusive job scheduling in PBS/Torque
The cluster resource manager Torque typically allocates compute nodes on an exclusive basis. However, when you have a lot of small jobs (like we do) running against multi-core compute nodes, this can ...
30
votes
6answers
7k views
Outgrowing cron: what's the next scheduler? [closed]
We've been using cron for about as long as I can remember to handle all of our job scheduling needs. Everything from storage clones/snapshots to reports against databases to daily system reports to ...
3
votes
2answers
5k views
Torque jobs does not enter “E” state (unless “qrun”)
Jobs I add to the queue stays there in "Queued" state without attempts to be executed (unless I manually qrun them)
/var/spool/torque/server_logs say just
04/11/2011 12:43:27;0100;PBS_Server;Job;16....
1
vote
2answers
3k views
Torque works half of the time. Fails No Permission the other half
We upgraded our OS from Debian 5 to Debian 6 and consequently upgraded Torque.
Now qstat and qsub works for about 1 minute and fails for another minute.
I have torque-2.5.5 (but I tried 2.4.8 and it ...
0
votes
3answers
866 views
Parallel prologue and epilogue in Grid Engine
We have a cluster being used to run MPI jobs for a customer. Previously this cluster used Torque as the scheduler, but we are transitioning to Grid Engine 6.2u5 (for some other features). ...
0
votes
1answer
4k views
Installing Torque on a single machine
Does anyone know if I can install Torque on a multicore machine instead of across a cluster? We're looking to test some software that requires Torque and exceeds the hardware capability of our LSF ...
0
votes
1answer
360 views
Only half of my pbs/Torque jobs are being scheduled
My supercomputing center recently moved from SGE to pbs/Torque. Now, when I schedule my array jobs, only half of the jobs in the array get scheduled. When they finish, the other half get scheduled. ...
