HPC Cluster Job Scheduler - Revision history

Admin at 17:14, 23 July 2025

2025-07-23T17:14:51Z

← Older revision		Revision as of 17:14, 23 July 2025
Line 13:		Line 13:
	The video below demonstrates a sample run of the tutorial steps described above.<br>'''NOTE: This video uses an older method for running the tutorial, but it still works.'''		The video below demonstrates a sample run of the tutorial steps described above.<br>'''NOTE: This video uses an older method for running the tutorial, but it still works.'''
	<br>		<br>
	<~~embedvideo service="~~youtube~~" urlargs="rel=0"~~>https://www.youtube.com/watch?v=yIM7NfCqUEg</~~embedvideo~~>		<youtube>https://www.youtube.com/watch?v=yIM7NfCqUEg</youtube>

	== Anatomy of a SLURM Sbatch Submit Script ==		== Anatomy of a SLURM Sbatch Submit Script ==

Admin: /* ELSA Job Partitions/Queues */

2024-12-10T20:52:19Z

ELSA Job Partitions/Queues

← Older revision		Revision as of 20:52, 10 December 2024
Line 286:		Line 286:
	\| nolimit<sup>*</sup> \|\| none \|\| CPU		\| nolimit<sup>*</sup> \|\| none \|\| CPU
	\|-		\|-
	\| gpu \|\| 7 days \|\| GPU		\| gpu \|\| 30 days \|\| GPU
	\|}		\|}
	<nowiki>*</nowiki> - Use of the '''nolimit''' partition is restricted to approved cluster users. Faculty may request access for themselves and students by emailing ssivy@tcnj.edu.		<nowiki>*</nowiki> - Use of the '''nolimit''' partition is restricted to approved cluster users. Faculty may request access for themselves and students by emailing ssivy@tcnj.edu.

Admin: /* ELSA Job Partitions/Queues */

2024-12-10T20:52:01Z

ELSA Job Partitions/Queues

← Older revision		Revision as of 20:52, 10 December 2024
Line 279:		Line 279:
	\|-		\|-
	! Parition/Queue Name!! Max Time Limit !! Resource Type		! Parition/Queue Name!! Max Time Limit !! Resource Type
	\|-
	~~\| short \|\| 6 hours \|\| CPU~~
	\|-		\|-
	\| normal \|\| 24 hours \|\| CPU		\| normal \|\| 24 hours \|\| CPU
	\|-		\|-
	\| long \|\| 7 days \|\| CPU		\| long \|\| 30 days \|\| CPU
	\|-		\|-
	\| nolimit<sup>*</sup> \|\| none \|\| CPU		\| nolimit<sup>*</sup> \|\| none \|\| CPU
	\|-
	~~\| amd \|\| 30 days \|\| CPU~~
	\|-
	~~\| shortgpu \|\| 6 hours \|\| GPU~~
	\|-		\|-
	\| gpu \|\| 7 days \|\| GPU		\| gpu \|\| 7 days \|\| GPU
	\|}		\|}
	<nowiki>*</nowiki> - Use of the '''nolimit''' partition is restricted to approved cluster users. Faculty may request access for themselves and students by emailing ssivy@tcnj.edu.		<nowiki>*</nowiki> - Use of the '''nolimit''' partition is restricted to approved cluster users. Faculty may request access for themselves and students by emailing ssivy@tcnj.edu.

Admin: /* Sample GPU Sbatch Submission Script */

2024-05-29T13:03:24Z

Sample GPU Sbatch Submission Script

← Older revision		Revision as of 13:03, 29 May 2024
Line 204:		Line 204:
	</pre>		</pre>

	While this line it the same as the other examples, you may also require include a line to include CUDA library support. CUDA is the library that includes the code for GPU-enabled programs. In our example, the '''elsa-tutorial''' module automatically loads the CUDA module. If it didn't, you would need to add a line like <code>module add ~~cua~~</code> in addition to the one listed.		While this line it the same as the other examples, you may also require include a line to include CUDA library support. CUDA is the library that includes the code for GPU-enabled programs. In our example, the '''elsa-tutorial''' module automatically loads the CUDA module. If it didn't, you would need to add a line like <code>module add cuda</code> in addition to the one listed.
	<pre>		<pre>
	module add elsa-tutorial		module add elsa-tutorial

Admin at 13:00, 29 May 2024

2024-05-29T13:00:46Z

← Older revision		Revision as of 13:00, 29 May 2024
Line 5:		Line 5:
	# Change to the <code>elsa-tutorial</code> directory. <pre>cd elsa-tutorial</pre>		# Change to the <code>elsa-tutorial</code> directory. <pre>cd elsa-tutorial</pre>
	# List the names of the files that were copied to the current directory. <pre>ls</pre>		# List the names of the files that were copied to the current directory. <pre>ls</pre>
	# Edit one of the submission scripts to modify the email address in it. This email address will receive messages when the job starts and ends or if there was some kind of failure. Use the simple text editor '''nano''' to edit the file. Press <code>CTRL q</code> to quit '''nano'''. <pre>nano submit-mpi.sh</pre>You could alternately use the edit feature in Open OnDemand to make the change.		# Edit one of the submission scripts to modify the email address in it. This email address will receive messages when the job starts and ends or if there was some kind of failure. Use the simple text editor '''nano''' to edit the file. Press <code>CTRL x</code> to exit/quit '''nano'''. <pre>nano submit-mpi.sh</pre>You could alternately use the edit feature in Open OnDemand to make the change.
	# Since the tutorial doesn't require any input file, you can simply submit this job to the cluster. <pre>sbatch submit-mpi.sh</pre>		# Since the tutorial doesn't require any input file, you can simply submit this job to the cluster. <pre>sbatch submit-mpi.sh</pre>
	# Monitor the status of your running job (which should only take about 20-25 seconds to run). The system will replace <code>$USER</code> in the command below with your username. You can also directly specify your username instead of <code>$USER</code>. <pre>squeue --user=$USER</pre>		# Monitor the status of your running job (which should only take about 20-25 seconds to run). The system will replace <code>$USER</code> in the command below with your username. You can also directly specify your username instead of <code>$USER</code>. <pre>squeue --user=$USER</pre>

Admin: /* Node Exclusivity */

2023-08-31T18:36:01Z

Node Exclusivity

← Older revision		Revision as of 18:36, 31 August 2023
Line 246:		Line 246:
	The job allocation can not share nodes with other running jobs.		The job allocation can not share nodes with other running jobs.

	This option should be used judiciously and sparingly. If for example, your job requires only 2 CPU cores and is scheduled on a node with 32 cores, no other job will be able to make use of the remaining 30 cores (not even your own job). Where this may make sense is when your job is competing for ~~memory (RAM)~~ with others running on the same node~~. The system is not yet configured to enforce memory limitations like it does for CPU cores~~. Using this option will guarantee that the entire node is exclusive to your job.		This option should be used judiciously and sparingly. If for example, your job requires only 2 CPU cores and is scheduled on a node with 32 cores, no other job will be able to make use of the remaining 30 cores (not even your own job). Where this may make sense is when your job is competing for network bandwidth or storage access with others running on the same node. Using this option will guarantee that the entire node is exclusive to your job.

	Example:		Example:

Admin: /* Submitting Your First HPC Job */

2022-06-15T15:31:29Z

Submitting Your First HPC Job

← Older revision		Revision as of 15:31, 15 June 2022
Line 11:		Line 11:
	# You can view the job output file by running the command (replace ##### with the actual job ID) <pre>cat job.####.out</pre>		# You can view the job output file by running the command (replace ##### with the actual job ID) <pre>cat job.####.out</pre>
	<br>		<br>
	The video below demonstrates a sample run of the tutorial steps described above. '''NOTE: ~~Video~~ uses an older method for running the tutorial, but it still works.'''		The video below demonstrates a sample run of the tutorial steps described above.<br>'''NOTE: This video uses an older method for running the tutorial, but it still works.'''
	<br>		<br>
	<embedvideo service="youtube" urlargs="rel=0">https://www.youtube.com/watch?v=yIM7NfCqUEg</embedvideo>		<embedvideo service="youtube" urlargs="rel=0">https://www.youtube.com/watch?v=yIM7NfCqUEg</embedvideo>

Admin: /* Submitting Your First HPC Job */

2022-06-15T15:31:05Z

Submitting Your First HPC Job

← Older revision		Revision as of 15:31, 15 June 2022
Line 11:		Line 11:
	# You can view the job output file by running the command (replace ##### with the actual job ID) <pre>cat job.####.out</pre>		# You can view the job output file by running the command (replace ##### with the actual job ID) <pre>cat job.####.out</pre>
	<br>		<br>
	The video below demonstrates a sample run of the tutorial steps described above.		The video below demonstrates a sample run of the tutorial steps described above. '''NOTE: Video uses an older method for running the tutorial, but it still works.'''
	<br>		<br>
	<embedvideo service="youtube" urlargs="rel=0">https://www.youtube.com/watch?v=yIM7NfCqUEg</embedvideo>		<embedvideo service="youtube" urlargs="rel=0">https://www.youtube.com/watch?v=yIM7NfCqUEg</embedvideo>

Admin: /* Submitting Your First HPC Job */

2022-06-15T15:28:09Z

Submitting Your First HPC Job

← Older revision		Revision as of 15:28, 15 June 2022
Line 2:		Line 2:
	# Login to the HPC cluster using one of the methods described in on [[HPC_Cluster_Getting_Started#Accessing_the_Cluster_via_SSH\|Accessing the Cluster via SSH]] on the Getting Started page.		# Login to the HPC cluster using one of the methods described in on [[HPC_Cluster_Getting_Started#Accessing_the_Cluster_via_SSH\|Accessing the Cluster via SSH]] on the Getting Started page.
	# Add the ELSA tutorial module <pre>module add elsa-tutorial</pre>		# Add the ELSA tutorial module <pre>module add elsa-tutorial</pre>
	# Run the setup script to make the <code>elsa-tutorial</code> directory and copy the example files to your account <pre>elsa-tutorial-setup.sh</pre>		# Run the setup script to make the <code>elsa-tutorial</code> directory and copy the example files to your account. <pre>elsa-tutorial-setup.sh</pre>
	# Change to the <code>elsa-tutorial</code> directory. <pre>cd elsa-tutorial</pre>		# Change to the <code>elsa-tutorial</code> directory. <pre>cd elsa-tutorial</pre>
	# List the names of the files that were copied to the current directory. <pre>ls</pre>		# List the names of the files that were copied to the current directory. <pre>ls</pre>

Admin: /* Submitting Your First HPC Job */

2022-06-15T15:27:52Z

Submitting Your First HPC Job

← Older revision		Revision as of 15:27, 15 June 2022
Line 1:		Line 1:
	== Submitting Your First HPC Job ==		== Submitting Your First HPC Job ==
	# Login to the HPC cluster using one of the methods described in on [[HPC_Cluster_Getting_Started#Accessing_the_Cluster_via_SSH\|Accessing the Cluster via SSH]] on the Getting Started page.		# Login to the HPC cluster using one of the methods described in on [[HPC_Cluster_Getting_Started#Accessing_the_Cluster_via_SSH\|Accessing the Cluster via SSH]] on the Getting Started page.
	# ~~Make a directory using~~ the ~~command~~ <pre>~~mkdir~~ tutorial</pre> ~~and then change into that directory using~~ <~~pre~~>cd tutorial</~~pre~~>		# Add the ELSA tutorial module <pre>module add elsa-tutorial</pre>
	~~# Next, make a~~ copy of the ~~submit script examples using~~ <pre>~~cp /opt/tcnjhpc/~~elsa-tutorial~~/examples/submit~~-* . </pre> ~~(make sure~~ to ~~include~~ the ~~'''.''' which represents the current~~ directory ~~as the target of the copy command)~~.		# Run the setup script to make the <code>elsa-tutorial</code> directory and copy the example files to your account <pre>elsa-tutorial-setup.sh</pre>
			# Change to the <code>elsa-tutorial</code> directory. <pre>cd elsa-tutorial</pre>
	# List the names of the files that were copied to the current directory. <pre>ls</pre>		# List the names of the files that were copied to the current directory. <pre>ls</pre>
	# Edit one of the submission scripts to modify the email address in it. This email address will receive messages when the job starts and ends or if there was some kind of failure. Use the simple text editor '''nano''' to edit the file. Press <code>CTRL q</code> to quit '''nano'''. <pre>nano submit-mpi.sh</pre>You could alternately use the edit feature in Open OnDemand to make the change.		# Edit one of the submission scripts to modify the email address in it. This email address will receive messages when the job starts and ends or if there was some kind of failure. Use the simple text editor '''nano''' to edit the file. Press <code>CTRL q</code> to quit '''nano'''. <pre>nano submit-mpi.sh</pre>You could alternately use the edit feature in Open OnDemand to make the change.