Usage of a HPC cluster - Revision history

Andrea Ferretti: /* Environment */

2021-04-30T07:37:04Z

Environment

← Older revision		Revision as of 07:37, 30 April 2021
Line 65:		Line 65:
	Make sure you load a proper parallel environment (incl MPI-aware compilers)		Make sure you load a proper parallel environment (incl MPI-aware compilers)

	~~Some examples~~:		One example:

	module purge		module purge
	module load psxe_2020		module load psxe_2020 # Intel 2020 compiler
			module load <more modules you are interested in, e.g. incl some QE distribution>

	These commands can be also place in the .bashrc file and most of the time need to be present		These commands can be also place in the .bashrc file and most of the time need to be present

2021-04-30T07:36:18Z

Environment

← Older revision		Revision as of 07:36, 30 April 2021
Line 68:		Line 68:

	module purge		module purge
	module load ~~psxe_2015~~		module load psxe_2020

	These commands can be also place in the .bashrc file and most of the time need to be present		These commands can be also place in the .bashrc file and most of the time need to be present

2021-04-30T07:29:04Z

← Older revision		Revision as of 07:29, 30 April 2021
Line 30:		Line 30:

	<user>: Unix username on the cluster login node		<user>: Unix username on the cluster login node
			<machine_host_name>: hostname (or IP) of the target HPC machine

			In order to access you need to have a working Unix username and passwd on the target machine.

			==Scheduler==

			Multiple schedulers are available. Examples include PBS Torque, IBM LoadLeveler and SLURM.
			Here we just cover some examples, providing the main commands to be used within the shell.

			===PBS Torque===
			* submitting a job
			qsub file.sh

			* monitoring a job
			qstat # general query, all jobs are shown
			qstat -u $USER # only my jobs
			qstat JID

			* checking queue properties
			qstat -q

			* deleting a job
			qdel JID

			JID (Job ID) is given by qstat

			* Interactive use on compute nodes
			qsub -I -q <queue_name>

			==Environment==

			Use the <code>module</code> command to manage the unix environment

			Make sure you load a proper parallel environment (incl MPI-aware compilers)

			Some examples:

			module purge
			module load psxe_2015

			These commands can be also place in the .bashrc file and most of the time need to be present
			in submission scripts

			In order to enquire the module system:
			module list # lists loaded modules
			module avail # lists available modules

2021-04-30T07:17:47Z

Structure of a HPC cluster

← Older revision		Revision as of 07:17, 30 April 2021
Line 19:		Line 19:
	* the above cluster structure is used from commodity local machines to large scale HPC architectures (as shown below for the Summit machine at Oak-Ridge Natl Lab (ORNL), TN, USA)		* the above cluster structure is used from commodity local machines to large scale HPC architectures (as shown below for the Summit machine at Oak-Ridge Natl Lab (ORNL), TN, USA)

	[[File:Summit ~~ORNL~~.jpg\|300px\|top]]		[[File:Summit-ONL.jpg\|300px\|top]]

	==Connecting==		==Connecting==

2021-04-30T07:16:39Z

Structure of a HPC cluster

← Older revision		Revision as of 07:16, 30 April 2021
Line 10:		Line 10:
	[[File:Logical structure HPC cluster.png\|500px\|top]]		[[File:Logical structure HPC cluster.png\|500px\|top]]

	The structure of a HPC system is sketched in the picture above.		The '''structure of a HPC system''' is sketched in the picture above.
	These are the main logical building blocks:		These are the main logical building blocks:

Line 17:		Line 17:
	* computation happens therefore asynchronously (in batch mode), and not on the login node.		* computation happens therefore asynchronously (in batch mode), and not on the login node.
	* a specific ''software environment'' is provided on the login node and on the compute node to run parallel jobs		* a specific ''software environment'' is provided on the login node and on the compute node to run parallel jobs
			* the above cluster structure is used from commodity local machines to large scale HPC architectures (as shown below for the Summit machine at Oak-Ridge Natl Lab (ORNL), TN, USA)

			[[File:Summit ORNL.jpg\|300px\|top]]

	==Connecting==		==Connecting==

2021-04-30T07:10:23Z

Structure of a HPC cluster

← Older revision		Revision as of 07:10, 30 April 2021
Line 13:		Line 13:
	These are the main logical building blocks:		These are the main logical building blocks:

	* a 'login node' is exposed to users for access (typically via <code>ssh</code>),		* a ''login node'' is exposed to users for access (typically via <code>ssh</code>),
	* a dedicated 'scheduler' (the 'queuing system') dispatches computational jobs to the 'compute nodes'		* a dedicated ''scheduler'' (the ''queuing system'') dispatches computational jobs to the ''compute nodes''
	* computation happens therefore asynchronously, and not on the login node.		* computation happens therefore asynchronously (in batch mode), and not on the login node.
	* a specific 'software environment' is provided on the login node and on the compute node to run parallel jobs		* a specific ''software environment'' is provided on the login node and on the compute node to run parallel jobs

	==Connecting==		==Connecting==

2021-04-30T07:09:43Z

Structure of a HPC cluster

← Older revision		Revision as of 07:09, 30 April 2021
Line 9:		Line 9:

	[[File:Logical structure HPC cluster.png\|500px\|top]]		[[File:Logical structure HPC cluster.png\|500px\|top]]

			The structure of a HPC system is sketched in the picture above.
			These are the main logical building blocks:

			* a 'login node' is exposed to users for access (typically via <code>ssh</code>),
			* a dedicated 'scheduler' (the 'queuing system') dispatches computational jobs to the 'compute nodes'
			* computation happens therefore asynchronously, and not on the login node.
			* a specific 'software environment' is provided on the login node and on the compute node to run parallel jobs

	==Connecting==		==Connecting==

2021-04-30T07:03:55Z

Structure of a HPC cluster

← Older revision		Revision as of 07:03, 30 April 2021
Line 8:		Line 8:
	==Structure of a HPC cluster==		==Structure of a HPC cluster==

	[[File:Logical structure HPC cluster.png\|~~300px~~\|~~left~~]]		[[File:Logical structure HPC cluster.png\|500px\|top]]

	==Connecting==		==Connecting==

2021-04-30T07:03:35Z

Structure of a HPC cluster

← Older revision		Revision as of 07:03, 30 April 2021
Line 8:		Line 8:
	==Structure of a HPC cluster==		==Structure of a HPC cluster==

	[[File:Logical structure HPC cluster.png~~\|thumb~~\|300px\|left]]		[[File:Logical structure HPC cluster.png\|300px\|left]]

	==Connecting==		==Connecting==

2021-04-30T07:03:25Z

Structure of a HPC cluster

← Older revision		Revision as of 07:03, 30 April 2021
Line 8:		Line 8:
	==Structure of a HPC cluster==		==Structure of a HPC cluster==

	[[File:Logical structure HPC cluster.png\|thumb\|~~150px~~\|left]]		[[File:Logical structure HPC cluster.png\|thumb\|300px\|left]]



	==Connecting==		==Connecting==