Computing Clusters - Revision history

Swlee49 at 18:28, 8 July 2011

2011-07-08T18:28:24Z

← Older revision		Revision as of 18:28, 8 July 2011
Line 28:		Line 28:
	MC2 has an intel compiler in the folder "/opt/intel", but it would not be active at your home directory. In this case, you need to activate an intel compiler at your home directory to compile somthing with icc (C compiler) and icpc (C++ compiler). You can do this simply by adding a line in your .bashrc file:		MC2 has an intel compiler in the folder "/opt/intel", but it would not be active at your home directory. In this case, you need to activate an intel compiler at your home directory to compile somthing with icc (C compiler) and icpc (C++ compiler). You can do this simply by adding a line in your .bashrc file:

	$source /opt/intel/Compiler/11.1/064/bin/iccvars.sh intel64		source /opt/intel/Compiler/11.1/064/bin/iccvars.sh intel64

	Because MC2 is a 64 bit machine, you need intel64. (If the machine is 32 bit, you need ia32). Then, log out of a machine and reconnect. Then, you can use the intel compiler at your home folder. This is needed to compile ParaDiS 2.5.1.		Because MC2 is a 64 bit machine, you need intel64. (If the machine is 32 bit, you need ia32). Then, log out of a machine and reconnect. Then, you can use the intel compiler at your home folder. This is needed to compile ParaDiS 2.5.1.

Swlee49 at 14:19, 8 July 2011

2011-07-08T14:19:04Z

← Older revision		Revision as of 14:19, 8 July 2011
Line 23:		Line 23:
	$ p4_error: semget failed for setnum:0		$ p4_error: semget failed for setnum:0
	If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Semapahores owned by other users, so you may have to contact them to free all Semaphores.		If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Semapahores owned by other users, so you may have to contact them to free all Semaphores.


			===Use Intel compiler in MC2===
			MC2 has an intel compiler in the folder "/opt/intel", but it would not be active at your home directory. In this case, you need to activate an intel compiler at your home directory to compile somthing with icc (C compiler) and icpc (C++ compiler). You can do this simply by adding a line in your .bashrc file:

			$source /opt/intel/Compiler/11.1/064/bin/iccvars.sh intel64

			Because MC2 is a 64 bit machine, you need intel64. (If the machine is 32 bit, you need ia32). Then, log out of a machine and reconnect. Then, you can use the intel compiler at your home folder. This is needed to compile ParaDiS 2.5.1.

Kwkang: /* Semaphores */

2011-01-05T05:05:28Z

Semaphores

← Older revision		Revision as of 05:05, 5 January 2011
Line 11:		Line 11:
	$ ./cleanipcs		$ ./cleanipcs
	This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Semapahores on the compute nodes, which can be cleaned using the '''cluster-fork''' command. The command '''cluster-fork''' runs a following command(''e.g.'' ./cleanipcs) on all nodes or a subset of nodes. To clean the compute nodes, use		This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Semapahores on the compute nodes, which can be cleaned using the '''cluster-fork''' command. The command '''cluster-fork''' runs a following command(''e.g.'' ./cleanipcs) on all nodes or a subset of nodes. To clean the compute nodes, use
	$ cluster-fork ./cleanipcs.		$ cluster-fork ./cleanipcs

			In some of clusters, the command '''cluster-fork''' has been replaced with '''rocks run host'''. In this case, use
			$ rocks run host "./cleanipcs"

	'''How do I know if I have a Semaphore problem?''' Ok, thats easy too. Just run the command		'''How do I know if I have a Semaphore problem?''' Ok, thats easy too. Just run the command

Kwkang: /* Computing Clusters */

2008-02-07T01:19:07Z

Computing Clusters

← Older revision		Revision as of 01:19, 7 February 2008
Line 1:		Line 1:
	==Computing Clusters==		==Computing Clusters==
	The Micro and Nano Mechanics Group primarily uses two clusters here at Stanford. They are MC-CC and WCR (or Glacial). MC-CC is a cluster supported by the Mechanics and Computation Group in the Mechanical Engineering Department and whose name means "Mechanics and Computation Computing Cluster". WCR, or alternatively Glacial, is a computer cluster hosted the the Mechanical Engineering Department and is the initials of the late William Reynolds (Not the Reynolds number Reynolds, but a Professor at Stanford who did research in thermodynamics). To use either cluster, you must be working with a faculty affiliated with the cluster. MC-CC has 45 nodes, each with 2 processors and WCR has 221 nodes with 8 processors per node.		The Micro and Nano Mechanics Group primarily uses two clusters here at Stanford. They are [http://hpcc.stanford.edu/clusters/mc-cc.html MC-CC] and WCR (or Glacial). MC-CC is a cluster supported by the Mechanics and Computation Group in the Mechanical Engineering Department and whose name means "Mechanics and Computation Computing Cluster". WCR, or alternatively Glacial, is a computer cluster hosted the the Mechanical Engineering Department and is the initials of the late William Reynolds (Not the Reynolds number Reynolds, but a Professor at Stanford who did research in thermodynamics). To use either cluster, you must be working with a faculty affiliated with the cluster. MC-CC has 45 nodes, each with 2 processors and WCR has 221 nodes with 8 processors per node.

	==Hints For working with the clusters==		==Hints For working with the clusters==

Kwkang: /* Computing Clusters */

2008-02-07T00:54:12Z

Computing Clusters

← Older revision		Revision as of 00:54, 7 February 2008
Line 1:		Line 1:
	==Computing Clusters==		==Computing Clusters==
	The Micro and Nano Mechanics Group primarily uses two clusters here at Stanford. They are MC-CC and WCR (or Glacial). MC-CC is a cluster supported by the Mechanics and Computation Group in the Mechanical Engineering Department and whose name means "~~Mechancs~~ and Computation Computing Cluster". WCR, or alternatively Glacial, is a computer cluster hosted the the Mechanical Engineering Department and is the initials of the late William ~~Renolds~~ (Not the Reynolds number Reynolds, but a Professor at Stanford who did research in thermodynamics). To use either cluster, you must be working with a faculty affiliated with the cluster. MC-CC has 45 nodes, each with 2 processors and WCR has 221 nodes with 8 processors per node.		The Micro and Nano Mechanics Group primarily uses two clusters here at Stanford. They are MC-CC and WCR (or Glacial). MC-CC is a cluster supported by the Mechanics and Computation Group in the Mechanical Engineering Department and whose name means "Mechanics and Computation Computing Cluster". WCR, or alternatively Glacial, is a computer cluster hosted the the Mechanical Engineering Department and is the initials of the late William Reynolds (Not the Reynolds number Reynolds, but a Professor at Stanford who did research in thermodynamics). To use either cluster, you must be working with a faculty affiliated with the cluster. MC-CC has 45 nodes, each with 2 processors and WCR has 221 nodes with 8 processors per node.

	==Hints For working with the clusters==		==Hints For working with the clusters==

Kwkang: /* Semaphores */

2008-02-07T00:53:35Z

Semaphores

← Older revision		Revision as of 00:53, 7 February 2008
Line 8:		Line 8:
	A [http://searchenterpriselinux.techtarget.com/sDefinition/0,,sid39_gci212959,00.html semaphore] is a type of shared resource on the clusters, that can lead to communication problems in parallel runs if left on the nodes since there is a limit of number of semaphores. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.		A [http://searchenterpriselinux.techtarget.com/sDefinition/0,,sid39_gci212959,00.html semaphore] is a type of shared resource on the clusters, that can lead to communication problems in parallel runs if left on the nodes since there is a limit of number of semaphores. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.

	'''How do I clean up Semahpores, you ask?''' Easy! You need to run the cleanipcs script to clean ~~semphores~~ from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute ~~privaleges~~. Now, you can run the program by typing		'''How do I clean up Semahpores, you ask?''' Easy! You need to run the cleanipcs script to clean semaphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privileges. Now, you can run the program by typing
	$ ./cleanipcs		$ ./cleanipcs
	This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with ~~Sempahores~~ on the compute nodes, which can be cleaned using the '''cluster-fork''' command. The command '''cluster-fork''' runs a following command(''e.g.'' ./cleanipcs) on all nodes or a subset of nodes. To clean the compute nodes, use		This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Semapahores on the compute nodes, which can be cleaned using the '''cluster-fork''' command. The command '''cluster-fork''' runs a following command(''e.g.'' ./cleanipcs) on all nodes or a subset of nodes. To clean the compute nodes, use
	$ cluster-fork ./cleanipcs.		$ cluster-fork ./cleanipcs.

Line 19:		Line 19:
	'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:		'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:
	$ p4_error: semget failed for setnum:0		$ p4_error: semget failed for setnum:0
	If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up ~~Sempahores~~ owned by other users, so you may have to contact them to free all Semaphores.		If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Semapahores owned by other users, so you may have to contact them to free all Semaphores.

Kwkang: /* Semaphores */

2008-02-07T00:52:42Z

Semaphores

← Older revision		Revision as of 00:52, 7 February 2008
Line 6:		Line 6:

	===Semaphores===		===Semaphores===
	A semaphore is a type of shared resource on the clusters that can lead to communication problems in ~~paralle~~ runs. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.		A [http://searchenterpriselinux.techtarget.com/sDefinition/0,,sid39_gci212959,00.html semaphore] is a type of shared resource on the clusters, that can lead to communication problems in parallel runs if left on the nodes since there is a limit of number of semaphores. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.

	'''How do I clean up Semahpores, you ask?''' Easy! You need to run the cleanipcs script to clean semphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privaleges. Now, you can run the program by typing		'''How do I clean up Semahpores, you ask?''' Easy! You need to run the cleanipcs script to clean semphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privaleges. Now, you can run the program by typing
	$ ./cleanipcs		$ ./cleanipcs
	This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Sempahores on the compute nodes, which can be cleaned using the cluster-fork command. To clean the compute nodes, use		This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Sempahores on the compute nodes, which can be cleaned using the '''cluster-fork''' command. The command '''cluster-fork''' runs a following command(''e.g.'' ./cleanipcs) on all nodes or a subset of nodes. To clean the compute nodes, use
	$ cluster-fork ./cleanipcs.		$ cluster-fork ./cleanipcs.

	'''How do I know if I have a Semaphore problem?''' Ok, thats easy too. Just run the command		'''How do I know if I have a Semaphore problem?''' Ok, thats easy too. Just run the command
	$/usr/bin/ipcs -s		$/usr/bin/ipcs -s
	This will list all of the Semaphore Arrays used on the head node. For the compute nodes, just use the cluster-fork prefix.		This will list all of the Semaphore Arrays used on the head node. Basically, the command '''ipcs''' lists all the active [http://en.wikipedia.org/wiki/Inter-process_communication interprocess communication] objects (shared memory, message queues and semaphores). With option '''-s''', it will show only semaphore sets. For the compute nodes, just use the cluster-fork prefix. The aforementioned script '''cleanipcs''' internally uses the command '''ipcrm''' to remove interprocess communication objects.

	'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:		'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:

Cweinber: /* Semaphores */

2008-02-06T23:36:12Z

Semaphores

← Older revision		Revision as of 23:36, 6 February 2008
Line 19:		Line 19:
	'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:		'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:
	$ p4_error: semget failed for setnum:0		$ p4_error: semget failed for setnum:0
	If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Sempahores owned by other users, so you may have to contact them to free all Semaphores~~. For this reason, cleaning up your Semaphores is good manners because it can affect all users~~.		If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Sempahores owned by other users, so you may have to contact them to free all Semaphores.

Cweinber: /* Semaphores */

2008-02-06T23:35:39Z

Semaphores

← Older revision		Revision as of 23:35, 6 February 2008
Line 8:		Line 8:
	A semaphore is a type of shared resource on the clusters that can lead to communication problems in paralle runs. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.		A semaphore is a type of shared resource on the clusters that can lead to communication problems in paralle runs. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.

	How do I clean up Semahpores, you ask? Easy! You need to run the cleanipcs script to clean semphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privaleges. Now, you can run the program by typing		'''How do I clean up Semahpores, you ask?''' Easy! You need to run the cleanipcs script to clean semphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privaleges. Now, you can run the program by typing
	$ ./cleanipcs		$ ./cleanipcs
	This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Sempahores on the compute nodes, which can be cleaned using the cluster-fork command. To clean the compute nodes, use		This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Sempahores on the compute nodes, which can be cleaned using the cluster-fork command. To clean the compute nodes, use
	$ cluster-fork ./cleanipcs.		$ cluster-fork ./cleanipcs.

	How do I know if I have a Semaphore problem? Ok, thats easy too. Just run the command		'''How do I know if I have a Semaphore problem?''' Ok, thats easy too. Just run the command
	$/usr/bin/ipcs -s		$/usr/bin/ipcs -s
	This will list all of the Semaphore Arrays used on the head node. For the compute nodes, just use the cluster-fork prefix.		This will list all of the Semaphore Arrays used on the head node. For the compute nodes, just use the cluster-fork prefix.

	Finally, how do I know if this is crashing my parallel job? Well, likely your job will crash with the following error:		'''Finally, how do I know if this is crashing my parallel job?''' Well, likely your job will crash with the following error:
	$ p4_error: semget failed for setnum:0		$ p4_error: semget failed for setnum:0
	If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Sempahores owned by other users, so you may have to contact them to free all Semaphores. For this reason, cleaning up your Semaphores is good manners because it can affect all users.		If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Sempahores owned by other users, so you may have to contact them to free all Semaphores. For this reason, cleaning up your Semaphores is good manners because it can affect all users.

Cweinber: /* Semaphores */

2008-02-06T23:35:00Z

Semaphores

← Older revision		Revision as of 23:35, 6 February 2008
Line 8:		Line 8:
	A semaphore is a type of shared resource on the clusters that can lead to communication problems in paralle runs. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.		A semaphore is a type of shared resource on the clusters that can lead to communication problems in paralle runs. If any job you run terminates abnormally, you may leave Semaphore Arrays on the computer. If you run the job on the head node, then the Semaphore Array is left with the head node, otherwise it will be associated with the compute node you were working on. This can lead to problems with future parallel jobs run by you or other users. Therefore, it is good manners to frequently clean up your Semaphores.

	How do I clean up Semahpores, you ask? Easy! You need to run the cleanipcs script to clean semphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privaleges. Now, you can run the program by typing ./cleanipcs. This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Sempahores on the compute nodes, which can be cleaned using the cluster-fork command. To clean the compute nodes, use		How do I clean up Semahpores, you ask? Easy! You need to run the cleanipcs script to clean semphores from your the computer. To do this, first you must find cleanipcs in the cluster using the locate command. Then, copy it over to you home directory and chmod it so that you have execute privaleges. Now, you can run the program by typing
			$ ./cleanipcs

			This will clean all of your Semaphores from the computer. However, if you are on a cluster, then this will only clean the Semaphores from the head node. Generally, the problem usually lies with Sempahores on the compute nodes, which can be cleaned using the cluster-fork command. To clean the compute nodes, use
	$ cluster-fork ./cleanipcs.		$ cluster-fork ./cleanipcs.

	How do I know if I have a Semaphore problem? Ok, thats easy too. Just run the command ~~/usr/bin/ipcs -s. This will list all of the Semaphore Arrays used on the head node. For the compute nodes, just use the cluster-fork prefix.~~		How do I know if I have a Semaphore problem? Ok, thats easy too. Just run the command
			$/usr/bin/ipcs -s
			This will list all of the Semaphore Arrays used on the head node. For the compute nodes, just use the cluster-fork prefix.

	Finally, how do I know if this is crashing my parallel job? Well, likely your job will crash with the following error: p4_error: semget failed for setnum:0. If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Sempahores owned by other users, so you may have to contact them to free all Semaphores. For this reason, cleaning up your Semaphores is good manners because it can affect all users.		Finally, how do I know if this is crashing my parallel job? Well, likely your job will crash with the following error:
			$ p4_error: semget failed for setnum:0
			If you see this error in your parallel job, you may have a problem with Semaphore Arrays. Run the ipcs command to see which nodes have Semaphore Arrays and clean up yours. You cannot clean up Sempahores owned by other users, so you may have to contact them to free all Semaphores. For this reason, cleaning up your Semaphores is good manners because it can affect all users.