Submitting a job to a queue - Revision history

Dvory at 06:54, 2 April 2024

2024-04-02T06:54:42Z

Dvory: /* Environment modules */

2024-03-17T13:58:59Z

Environment modules

Dvory at 13:28, 19 January 2023

2023-01-19T13:28:58Z

Eyal at 14:34, 14 December 2022

2022-12-14T14:34:03Z

Levk: 13 revisions imported

2022-04-05T08:33:39Z

13 revisions imported

orig>Wiki admin at 06:41, 23 January 2022

2022-01-23T06:41:13Z

orig>Wiki admin at 08:35, 27 May 2021

2021-05-27T08:35:58Z

orig>Wiki admin: /* Quesues list */

2021-05-13T10:35:44Z

Quesues list

orig>Wiki admin: /* Quesues list */

2021-05-13T10:34:39Z

Quesues list

orig>Wiki admin: /* Quesues list */

2021-05-13T10:32:15Z

Quesues list

@@ Line 128: / Line 128: @@
 myTable.m ⇒ This matlab file calculates something
 <pre>
 fprintf('=======================================\n');
 fprintf(' a             b             c              d             \n');
@@ Line 160: / Line 159: @@
 cd /a/home/cc/tree/taucc/staff/dvory/matlab
-matlab -nodisplay -r "myTable()"
+matlab -nodisplay -nosplash -nodesktop -r "run(myTable());exit;"
 </pre>

@@ Line 227: / Line 227: @@
 Useful commands:
 <pre>
-module avail
+module avail <required module>
 </pre>
 ⇒ lists the available modules on the system

← Older revision		Revision as of 13:28, 19 January 2023
Line 246:		Line 246:
	</pre>		</pre>
	⇒ unloads the loaded module		⇒ unloads the loaded module
		+
		+	===GPU usage===
		+	When not asking for a specific gpu, the code actually asks by default the first one, which may be busy, or using all its memory.
		+	In order to specify a gpu to be used, need to define it (using the environment variable: CUDA_VISIBLE_DEVICES)
		+	e.g.
		+	<pre>
		+	export CUDA_VISIBLE_DEVICES=2
		+	</pre>
		+	If one would like to use more than 1 gpu, she may type them separated with comma, e.g.
		+	<pre>
		+	export CUDA_VISIBLE_DEVICES="2,4"
		+	</pre>
		+	In order to know which gpus are free, one may copy python script to local disk and activate it:
		+	<pre>
		+	module load python/python-anaconda_3.7
		+	python /powerapps/scripts/check_avail_gpu.py
		+	</pre>
		+	It will output the first free gpu (in its last line)
		+	If need more than one gpu, need to overwrite parameter num_gpus in line 96
		+	num_gpus = 1
		+	- it needs to be changed it to the number of needed gpus

@@ Line 13: / Line 13: @@
 Start with one of the below commands:
 <pre>
-ssh <username>@powerlogin9.tau.ac.il
+ssh <username>@power9login.tau.ac.il
 ssh powerlogin9.tau.ac.il -l <username>
 </pre>

@@ Line 23: / Line 23: @@
 </pre>
-Send the script to be executed in one of the existing queues, for example, to queue ‘short’:
+Send the script to be executed in one of the existing queues, for example, to queue ‘public’:
 <pre>
 qsub -q public script

← Older revision	Revision as of 08:33, 5 April 2022
(No difference)

@@ Line 3: / Line 3: @@
 The Faculty Computer Coordinators can change their netgroup from general to power.
-Users’ jobs are executed on the compute nodes (compute-0-0 – compute-0-249) under control of a queuing system (PBSPRO). Users are able to logon to the head node, power, via ssh (where their home directory is mounted from the CC filer, the same as on the other CC servers) and submit their jobs to the batch system.
+Users’ jobs are executed on the compute nodes (compute-0-0 – compute-0-500) under control of a queuing system (PBSPRO). Users are able to logon to the head node, power, via ssh (where their home directory is mounted from the CC filer, the same as on the other CC servers) and submit their jobs to the batch system.
 Power cluster and pbspro queueing system
@@ Line 13: / Line 13: @@
 Start with one of the below commands:
 <pre>
-ssh <username>@powerlogin.tau.ac.il
+ssh <username>@powerlogin9.tau.ac.il
-ssh powerlogin.tau.ac.il -l <username>
+ssh powerlogin9.tau.ac.il -l <username>
 </pre>
 Create a batch job script, for example, file named script that contains the following lines:
@@ Line 73: / Line 73: @@
 qsub -q power-dvory -lmem=14gb,pmem=5gb,vmem=20gb,pvmem=20gb <script>
 qsub -q gpu -lngpus=1 <script>
-qsub -q public -lnodes=1:ppn=4 <script>
+qsub -q public -lselect=1:ncpus=4 <script>
 </pre>
 While:
@@ Line 115: / Line 115: @@
 Explanations regarding PBS script directives can be found at: https://www.osc.edu/supercomputing/batch-processing-at-osc/pbs-directives-summary
-For example, instead of specifying ‘qsub –q hugemem …’, one may add ‘#PBS –q hugemem’ to the script to be executed. Like in the below script, named ‘script.sh’, which can be run using the command: ‘qsub script.sh’
+For example, instead of specifying ‘qsub –q public …’, one may add ‘#PBS –q public’ to the script to be executed. Like in the below script, named ‘script.sh’, which can be run using the command: ‘qsub script.sh’
 <pre>
 #!/bin/bash
 #PBS -l walltime=1:00:00
-#PBS -l nodes=1:ppn=4,mem=400mb
+#PBS -l select=1:ncpus=4,mem=400mb
 ./my application
 </pre>
@@ Line 196: / Line 196: @@
 Login to power.tau.ac.il with ‘X’:
 <pre>
-ssh -X -l <username> powerlogin.tau.ac.il
+ssh -X -l <username> powerlogin9.tau.ac.il
 </pre>
 Then use the qsub command with ‘-X’:
@@ Line 213: / Line 213: @@
 Parallel jobs can be executed in the cluster - using up to 96 cores (=ppn) for a job. For example, jobs compiled with mpich can be submitted with the following command:
 <pre>
-qsub -l nodes=1:ppn=8 -q parallel <script-filename>
+qsub -l select=1:ncpus=8 -q paublic <script-filename>
 </pre>
 Multithreaded matlab jobs can be submitted with the following command:
 <pre>
-qsub -l nodes=1:ppn=8 -q parallel <matlab-script>
+qsub -l select=1:ncpus=8 -q parallel <matlab-script>
 </pre>
 ‘-l’ refers to a small ‘L’

@@ Line 92: / Line 92: @@
 The more updated syntax includes the word 'select'
-====Quesues list====
 '''gpu''' – this queue’s purpose it to enable running jobs, which require gpu processing

@@ Line 123: / Line 123: @@
 <pre>
 function [] = myTable()
 fprintf('=======================================\n');
 fprintf(' a             b             c              d             \n');
 fprintf('=======================================\n');
 while 1
                  for j = 1:10
                                  a = sin(10*j);
                                  b = a*cos(10*j);
                                  c = a + b;
                                  d = a - b;
                                  fprintf('%+6.5f   %+6.5f   %+6.5f   %+6.5f   \n',a,b,c,d);
                  end
 end
 fprintf('=======================================\n');
 </pre>
 my_table_script.sh ⇒ This script executes the matlab program. Need just to run qsub with this script
@@ Line 188: / Line 174: @@
 ./run_in_loop.sh
 </pre>
 ===Interactive session===