Commit 2e694397 authored by Michael Krause's avatar Michael Krause 🎉
Browse files

RM: consistency in torque

parent 6ac169ef
Torque **(EOL)**
================
Torque **(End-Of-Life)**
========================
`Torque`_ is a **PBS**-based resource manager, originally developed by NASA and
currently maintained by Adaptive Computing Inc. A necessary, but problematic
......
......@@ -28,7 +28,7 @@ You can then submit that job with ``qsub simple_job.pbs``.
Now that is rarely sufficient. In most cases you are going to need some
resource requests and a state variable as you are very likely to submit
multiple similar jobs. It is possible to add qsub parameters (see
:doc:`resources`) inside the job file.
:ref:`torque_resources`) inside the job file.
Example ``job_with_resources.pbs``
......
......@@ -9,28 +9,28 @@ those options need the prefix ``#PBS`` and must be stated in the first section
of the file before the actual commands. The complete list can be found in ``man
pbs_resources``.
#PBS -N *job-name*
``#PBS -N job-name``
Sets the name of the job. This is mostly useful when submitting lot's of
similar jobs in a loop.
#PBS -l *walltime=100:0:0*
``#PBS -l walltime=100:0:0``
Sets the expected maximum running time for the job. When a job **exceeds**
those limits it will **be terminated**.
#PBS -l *mem=10gb*
``#PBS -l mem=10gb``
Sets another resource requirement: memory. Exceeding this value in a job is
even more crucial than running time as you might interfere with other jobs
on the node. Therefor it needs to be **terminated as well**.
#PBS -d *project/data*
``#PBS -d project/data``
Sets the working directory of the job. Every time a job gets started it
will spawn a shell on some node. To initially jump to some directory use
this option. *Otherwise* the first command of your job should always be ``cd
project/data``.
#PBS -o */home/mpib/krause/logs/*
``#PBS -o /home/mpib/krause/logs/``
Specify the location where Torque will save the jobs' log file. The
*stdout* and *stderr* streams will be saved into a file called
``<jobname>.o<jobid>`` and ``<jobname>.e<jobid>`` in the current location
......@@ -38,24 +38,24 @@ pbs_resources``.
log in that file. If it's a directory it will put the logs into that
directory with the default naming scheme.
#PBS -o */dev/null*
``#PBS -o /dev/null``
To discard all standard output log use the special file ``/dev/null``.
#PBS -e */dev/null*
``#PBS -e /dev/null``
The same is true for the standard error log stream.
#PBS -j *oe*
``#PBS -j oe``
This option will tell torque to merge stderr into stdout and only store
a single file.
#PBS -j *eo*
``#PBS -j eo``
This will merge stdout into stderr instead.
#PBS -M *krause[,knope,dwyer]*
``#PBS -M krause[,knope,dwyer]``
Send an e-mail to a single user or a list of users in case there is
a configured event.
#PBS -m *<str>*
``#PBS -m <str>``
This paramter defines e-mail events. You can use a combination of **a,b,e**
or the single value **n**:
......@@ -63,11 +63,11 @@ pbs_resources``.
+ **b** defines the beginning of a job run as event
+ **e** send an e-mail when the job has finished
#PBS -W *depend=afterok:*\ Job-Id
``#PBS -W depend=afterok:\ Job-Id``
This will add a dependency to the current job. It will only be started or
tagged as startable when another job with id *Job-Id* finished
successfully.
#PBS -h
``#PBS -h``
Set the job in a holding state. This will prevent it from being started.
Release the hold with ``qrls <jobid>``.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment