Differences

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

--- doku:slurm [2023/03/14 12:47] – [Job chain] goldenberg
+++ doku:slurm [2024/02/07 10:55] (current) – [The job submission script] katrin
@@ Line 41: / Line 41: @@
 ==== Node allocation policy ====
-On VSC-4 there are a set of nodes which accept jobs that do not require entire nodes (anythong from 1 core to less than a full node). These nodes are set up to accomodate different jobs from different users until they are full. They are automatically used for such types of jobs. All other nodes are assigned completely to a job.
+On VSC-4 & VSC-5 there is a set of nodes that accept jobs that do not require entire exclusive nodes (anything from 1 core to less than a full node). These nodes are set up to accommodate different jobs from different users until they are full. They are automatically used for such types of jobs. All other nodes are assigned completely (and exclusively) to a job whenever the '-N' argument is used.
-On VSC-5 that feature is not yet active, so only complete nodes are assigned to jobs.
@@ Line 56: / Line 56: @@
 It is recommended to write the job script using a [[doku:win2vsc&#the_job_filetext_editors_on_the_cluster|text editor]] on the VSC //Linux// cluster or on any Linux/Mac system.
-Editors in //Windows// may add additional invisible characters to the job file which render it unreadable and, thus, it is not executed.
+Editors in //Windows// may add additional invisible characters to the job file which render it unreadable and, thus, it cannot be not executed.
 Assume a submission script ''check.slrm''
@@ Line 76: / Line 76: @@
 </code>
   * **-J**     job name,\\
-  * **-N**     number of nodes requested (16 cores per node available)\\
+  * **-N**     number of nodes requested\\
   * **-n, --ntasks=<number>** specifies the number of tasks to run,
   * **--ntasks-per-node**     number of processes run in parallel on a single node \\
@@ Line 272: / Line 272: @@
 #SBATCH -J par                      # job name
 #SBATCH -N 2                        # number of nodes=2
-#SBATCH --ntasks-per-node=16        # uses all cpus of one node
+#SBATCH --ntasks-per-node=48        # uses all cpus of one node
 #SBATCH --ntasks-per-core=1
 #SBATCH --threads-per-core=1
@@ Line 282: / Line 282: @@
 rm machines_tmp
-tasks_per_node=16         # change number accordingly
+tasks_per_node=48         # change number accordingly
 nodes=2                   # change number accordingly
 for ((line=1; line<=nodes; line++))
@@ Line 334: / Line 334: @@
   - continue at 2. for further dependent jobs
-===== Licenses =====
-Software, that uses a license server, has to be specified upon job submission. A list of all available licensed software for your user can be shown by using the command:
-<code>
-slic
-</code>
-Within the job script add the flags as shown with 'slic', e.g. for using both Matlab and Mathematica:
-<code>
-#SBATCH -L matlab@vsc,mathematica@vsc
-</code>
 ===== Prolog Error Codes =====