HPCC usage rules - Revision history

WikiSysop: Text replacement - "http://csdms.colorado.edu" to "https://csdms.colorado.edu"

2018-02-19T23:27:45Z

Text replacement - "http://csdms.colorado.edu" to "https://csdms.colorado.edu"

← Older revision		Revision as of 17:27, 19 February 2018
Line 509:		Line 509:

	== Monitoring the CSDMS HPCC (Beach) ==		== Monitoring the CSDMS HPCC (Beach) ==
	Beach is equipped with a monitoring system named '''Ganglia'''. Ganglia reports real time information of how active the beach cluster is used, overall as well as on a node basis. You can see the activity on beach by going to the following site: ~~http~~://csdms.colorado.edu/ganglia		Beach is equipped with a monitoring system named '''Ganglia'''. Ganglia reports real time information of how active the beach cluster is used, overall as well as on a node basis. You can see the activity on beach by going to the following site: https://csdms.colorado.edu/ganglia

Mpiper: Touch up PBS command table

2017-04-14T21:42:08Z

Touch up PBS command table

← Older revision		Revision as of 15:42, 14 April 2017
Line 168:		Line 168:

	<syntaxhighlight lang=bash>		<syntaxhighlight lang=bash>
	#PBS -r n # The job is not rerunnable.		#PBS -r n # The job is not rerunnable
	#PBS -r y # The job is rerunnable		#PBS -r y # The job is rerunnable
	#PBS -q testq # The queue to submit to		#PBS -q testq # The queue to submit to
Line 174:		Line 174:
	#PBS -o testjob.out # The file to print the output to		#PBS -o testjob.out # The file to print the output to
	#PBS -e testjob.err # The file to print the error to		#PBS -e testjob.err # The file to print the error to
	~~# Mail Directives~~		#PBS -m abe # Send email at these points in the execution
	#PBS -m abe # ~~The~~ points ~~durring~~ the execution ~~to send an email~~		#PBS -M me@colorado.edu # Whom to email
	#PBS -M me@colorado.edu # ~~Who~~ to ~~Mail to~~

	#PBS -l walltime=01:00:00 # Specify the walltime		#PBS -l walltime=01:00:00 # Specify the walltime
	#PBS -l pmem=100mb # Memory ~~Allocation~~ for the Job		#PBS -l pmem=100mb # Memory allocation for the Job
	#PBS -l nodes=4 # Number of nodes to ~~Allocate~~		#PBS -l nodes=4 # Number of nodes to allocate

	#PBS -l nodes=4:ppn=3 # Number of nodes and the number processors per node		#PBS -l nodes=4:ppn=3 # Number of nodes and the number processors per node
	</syntaxhighlight>		</syntaxhighlight>

Mpiper: Words

2017-02-17T17:26:29Z

Words

← Older revision		Revision as of 11:26, 17 February 2017
Line 12:		Line 12:
	There are essentially two ways to achieve this: (1) to use the PBS [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/6-dataManagement/fileStaging.htm stagein and stageout] utilities, or (2) to manually copy the files by commands in your submission script. The stagein and stageout features of Torque are somewhat awkward, especially since wildcards and macros in the file lists cannot be used. This method also has some timing issues. Hence, we ask you to use the second method, and to use secure copy (scp) to do the file transfers to avoid [http://en.wikipedia.org/wiki/Network_file_system NFS] bottlenecks. An example of how the second method might be done is given below in the [[Help:HPCC_Torque#Example_Torque_Scripts \| serial example]].		There are essentially two ways to achieve this: (1) to use the PBS [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/6-dataManagement/fileStaging.htm stagein and stageout] utilities, or (2) to manually copy the files by commands in your submission script. The stagein and stageout features of Torque are somewhat awkward, especially since wildcards and macros in the file lists cannot be used. This method also has some timing issues. Hence, we ask you to use the second method, and to use secure copy (scp) to do the file transfers to avoid [http://en.wikipedia.org/wiki/Network_file_system NFS] bottlenecks. An example of how the second method might be done is given below in the [[Help:HPCC_Torque#Example_Torque_Scripts \| serial example]].

	== ~~The~~ TORQUE ~~Cheat Sheet~~ ==		== TORQUE Commands ==

	To use TORQUE, you will probably want to add their locations to your path. For the CSDMS HPCC, these directories are:		To use TORQUE, you will probably want to add their locations to your path. For the CSDMS HPCC, these directories are:

Mpiper: Rename Torque to TORQUE

2017-02-17T17:08:14Z

Rename Torque to TORQUE

Show changes

Mpiper: Use Albert's new PageTitle class

2017-02-17T17:02:44Z

Use Albert's new PageTitle class

← Older revision		Revision as of 11:02, 17 February 2017
Line 1:		Line 1:
	~~= Submitting Jobs to the CSDMS~~ HPCC =		{{PageTitle\|HPCC usage rules}}
			<div>{{TOC limit\|2}}</div>

	The CSDMS High Performance Computing Cluster uses Torque as a job scheduler. With Torque you can allocate resources, schedule and manage job execution, monitor and view the status of your jobs.		The CSDMS High Performance Computing Cluster uses Torque as a job scheduler. With Torque you can allocate resources, schedule and manage job execution, monitor and view the status of your jobs.
Line 13:		Line 14:
	== The Torque Cheat Sheet ==		== The Torque Cheat Sheet ==

	~~=== Installation Locations ===~~
	To use Torque, you will probably want to add their locations to your path. For the CSDMS HPCC, these directories are:		To use Torque, you will probably want to add their locations to your path. For the CSDMS HPCC, these directories are:
	* Torque: <tt>/opt/torque/bin</tt>		* Torque: <tt>/opt/torque/bin</tt>
Line 511:		Line 511:
	</syntaxhighlight>		</syntaxhighlight>

	= Monitoring the CSDMS HPCC (Beach) =		== Monitoring the CSDMS HPCC (Beach) ==
	Beach is equipped with a monitoring system named '''Ganglia'''. Ganglia reports real time information of how active the beach cluster is used, overall as well as on a node basis. You can see the activity on beach by going to the following site: http://csdms.colorado.edu/ganglia		Beach is equipped with a monitoring system named '''Ganglia'''. Ganglia reports real time information of how active the beach cluster is used, overall as well as on a node basis. You can see the activity on beach by going to the following site: http://csdms.colorado.edu/ganglia

Mpiper: Add list of variables passed from parent environment

2016-07-14T16:05:46Z

Add list of variables passed from parent environment

← Older revision		Revision as of 10:05, 14 July 2016
Line 219:		Line 219:
	</syntaxhighlight>		</syntaxhighlight>

	=== ~~Torque~~ environment variables ===		=== Environment variables ===
	~~Before~~ Torque ~~runs your script it~~ defines a set of environment variables ~~that you~~ can use ~~anywhere within your script. That is, either~~ in PBS directives or in commands. For example,
			The <tt>qsub</tt> command passes a limited set of environment variables from your shell environment to the job.
			They include:
			{\|
			! align=left width=200 \| Variable Name
			! align=left \| Description
			\|-
			\| HOME
			\| The path to your home directory.
			\|-
			\| LANG
			\| Sets the locale; e.g., <tt>en_US.UTF-8</tt>.
			\|-
			\| LOGNAME
			\| Your login name.
			\|-
			\| PATH
			\| A list of directories to be searched for executables.
			\|-
			\| SHELL
			\| The shell that you're using; e.g., bash, csh, tcsh.
			\|}

			Torque also defines a set of environment variables.
			You can use these environment variables in PBS directives or in commands.
			For example,
	<syntaxhighlight lang=bash>		<syntaxhighlight lang=bash>
	#!/bin/sh		#!/bin/sh
	#PBS -N example_job		#PBS -N example_job
	#PBS -l mem=2gb		#PBS -l mem=2gb
	#PBS -o ~~my_job~~.out		#PBS -o $PBS_JOBNAME.out
	#PBS -e ~~my_job~~.err		#PBS -e $PBS_JOBNAME.err

	IN_FILE=${PBS_O_HOME}/my_input_file.txt		IN_FILE=${PBS_O_HOME}/my_input_file.txt
Line 232:		Line 257:
	my_prog ${IN_FILE}		my_prog ${IN_FILE}
	</syntaxhighlight>		</syntaxhighlight>
	~~Torque has set the environment variable <tt>PBS_O_HOME</tt> to be the home directory on which the <tt>qsub</tt> command was run.~~

	The following environment variables relate to the '''''machine on which <tt>qsub</tt> was executed''''':		The following environment variables relate to the '''''machine on which <tt>qsub</tt> was executed''''':
Line 243:		Line 267:
	\|-		\|-
	\| PBS_O_LOGNAME		\| PBS_O_LOGNAME
	\| The login name of the user running qsub.		\| The login name of the user running <tt>qsub</tt>.
	\|-		\|-
	\| PBS_O_HOME		\| PBS_O_HOME
	\| Home directory of the user running qsub.		\| Home directory of the user running <tt>qsub</tt>.
	\|-		\|-
	\| PBS_O_WORKDIR		\| PBS_O_WORKDIR
	\| The working directory (the directory where qsub was executed).		\| The working directory (the directory where <tt>qsub</tt> was executed).
	\|-		\|-
	\| PBS_O_QUEUE		\| PBS_O_QUEUE

Mpiper: Formatting

2015-11-05T16:38:27Z

Formatting

← Older revision		Revision as of 10:38, 5 November 2015
Line 135:		Line 135:
	If you want to delete a job that you already submitted, use the <tt>qdel</tt> command. This immediately removes your job from the queue and kills it if it is already running. To delete the job from the previous example (job number 45),		If you want to delete a job that you already submitted, use the <tt>qdel</tt> command. This immediately removes your job from the queue and kills it if it is already running. To delete the job from the previous example (job number 45),
	<syntaxhighlight lang=text>		<syntaxhighlight lang=text>
	>qdel 45		> qdel 45
	</syntaxhighlight>		</syntaxhighlight>

Line 141:		Line 141:
	Use <tt>qstat</tt> to check the status of a job. This returns a brief status report of all your jobs that are either queued or running. For example,		Use <tt>qstat</tt> to check the status of a job. This returns a brief status report of all your jobs that are either queued or running. For example,
	<syntaxhighlight lang=text>		<syntaxhighlight lang=text>
	>qstat		> qstat
	Job id Name User Time Use S Queue		Job id Name User Time Use S Queue
	------------------------- ---------------- --------------- -------- - -----		------------------------- ---------------- --------------- -------- - -----

Mpiper: Update sample qsub output

2015-11-05T16:36:19Z

Update sample qsub output

← Older revision		Revision as of 10:36, 5 November 2015
Line 126:		Line 126:
	> qsub run_my_prog.sh		> qsub run_my_prog.sh
	</syntaxhighlight>		</syntaxhighlight>
	where the contents of the file <tt>run_my_prog.sh</tt> is code snippet above. Torque will respond with the job number and ~~ib-net~~,		where the contents of the file <tt>run_my_prog.sh</tt> is code snippet above. Torque will respond with the job number and location,
	<syntaxhighlight lang=text>		<syntaxhighlight lang=text>
	45.~~ib-net~~		45.beach.colorado.edu
	</syntaxhighlight>		</syntaxhighlight>
	In this case Torque has identified your job with job number 45. You have now submitted your job to the default queue and will be run as soon as there are resources available for it. By default, the standard error and output of your script are redirected to files in your home directory. They will have the name <tt><job_name>.o<job_no></tt>, and <tt><job_name>.e<job_no></tt> for standard output and error, respectively. Thus, for our example, standard output will be written to <tt>run_my_prog.sh.o45</tt>, and standard error will be written to <tt>run_my_prog.sh.e.45</tt>.		In this case Torque has identified your job with job number 45. You have now submitted your job to the default queue and will be run as soon as there are resources available for it. By default, the standard error and output of your script are redirected to files in your home directory. They will have the name <tt><job_name>.o<job_no></tt>, and <tt><job_name>.e<job_no></tt> for standard output and error, respectively. Thus, for our example, standard output will be written to <tt>run_my_prog.sh.o45</tt>, and standard error will be written to <tt>run_my_prog.sh.e.45</tt>.

Mpiper: Update broken links

2015-11-04T21:47:55Z

Update broken links

← Older revision		Revision as of 15:47, 4 November 2015
Line 279:		Line 279:
	You can check the status of your jobs with Torque.		You can check the status of your jobs with Torque.

	Torque provides the [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ <tt>qstat</tt>] command to check job status. Please see the qstat man page for a full list of options (<tt>man qstat</tt>). Some useful options that were not listed above include:		Torque provides the [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm <tt>qstat</tt>] command to check job status. Please see the qstat man page for a full list of options (<tt>man qstat</tt>). Some useful options that were not listed above include:

	{\|		{\|
Line 285:		Line 285:
	! align=left \|Description		! align=left \|Description
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -n		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -n
	\| Show which nodes are allocated to each job.		\| Show which nodes are allocated to each job.
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -f		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -f
	\| Show a full status display.		\| Show a full status display.
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -u		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -u
	\| Show status for jobs owned by a specified user.		\| Show status for jobs owned by a specified user.
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -q		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -q
	\| Show status for a particular queue.		\| Show status for a particular queue.
	\|}		\|}

Mpiper: Update broken links

2015-11-04T21:46:44Z

Update broken links

← Older revision		Revision as of 15:46, 4 November 2015
Line 51:		Line 51:
	! align=left width=300 \| Description		! align=left width=300 \| Description
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -q		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -q
	\| List all queues		\| List all queues
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -a		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -a
	\| List all jobs		\| List all jobs
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -au <userid>		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -au <userid>
	\| list jobs for userid		\| list jobs for userid
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -r		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -r
	\| List running jobs		\| List running jobs
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -f <job_id>		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -f <job_id>
	\| List full information about job_id		\| List full information about job_id
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -Qf <queue>		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -Qf <queue>
	\| List full information about queue		\| List full information about queue
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/qstat.~~shtml~~ qstat] -B		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/qstat.htm qstat] -B
	\| List summary status of the job server		\| List summary status of the job server
	\|-		\|-
	\| [http://~~www~~.~~clusterresources~~.com/~~torquedocs21~~/commands/pbsnodes.~~shtml~~ pbsnodes]		\| [http://docs.adaptivecomputing.com/torque/6-0-0/help.htm#topics/torque/commands/pbsnodes.htm pbsnodes]
	\| List status of all compute nodes		\| List status of all compute nodes
	\|}		\|}