191
edits
Changes
Jump to navigation
Jump to search
Line 1:
Line 1: + + + Line 38:
Line 41: + Line 49:
Line 53: − + + + + Line 107:
Line 114: + Line 149:
Line 157: − + Line 168:
Line 176: + Line 219:
Line 228: − == Long job submit files == − In order to submit a long job on the cluster the following line needs to be added to the submit file − <pre> − +AccountingGroup = “group_statistics_longjob.prod” − </pre> − Please note that long jobs have a maximum of 48 hours before they may be killed. The cluster is optimal for many small jobs, not a few long jobs.
no edit summary
== GCC 4.9.2 ==
The default GCC for CentOS 6 is 4.4.7 which will be used when running your jobs. Please see [http://gryphn.phys.uconn.edu/statswiki/index.php/How_to_Submit_a_Job#GCC_4.9.2 this section] regarding the use of GCC 4.9.2.
== C example ==
== C example ==
=== The Problem and the Code ===
=== The Problem and the Code ===
<pre>Executable = calcpi
<pre>Executable = calcpi
Requirements = ParallelSchedulingGroup == "stats group"
Requirements = ParallelSchedulingGroup == "stats group"
+AccountingGroup = "group_statistics_testjob.username"
Universe = vanilla
Universe = vanilla
output = calcpi$(Process).out
output = calcpi$(Process).out
The last line specifies that 50 instances should be scheduled on the cluster. The description file specifies the executable and the arguments passed to it during execution. (In this case we are requesting that all instances iterate 10e9 times in the program's sampling loop.) The requirement field insists that the job stay on the Statistics Cluster. (All statistics nodes are labeled with "stats group" in their Condor ClassAds) Output and error files are targets for standard out and standard error streams respectively. The log file is used by Condor to record in real time the progress in job processing. Note that this setup labels output files by process number to prevent a job instance from overwritting files belonging to another. The current values imply that all files are to be found in the same directory as the description file.
The last line specifies that 50 instances should be scheduled on the cluster. The description file specifies the executable and the arguments passed to it during execution. (In this case we are requesting that all instances iterate 10e9 times in the program's sampling loop.) The requirement field insists that the job stay on the Statistics Cluster. (All statistics nodes are labeled with "stats group" in their Condor ClassAds) Output and error files are targets for standard out and standard error streams respectively. The log file is used by Condor to record in real time the progress in job processing. Note that this setup labels output files by process number to prevent a job instance from overwritting files belonging to another. The current values imply that all files are to be found in the same directory as the description file.
The <i>universe</i> variable specifies the condor runtime environment. For the purposes of these independent jobs, the simplest "vanilla" universe suffices. In a more complicated parallel task, with checkpointing and migration, MPI calls etc., more advanced run-time environments are employed, often requiring specilized linking of the binaries. The lines specifying transfer settings are important to avoid any assumptions about accessibility over nfs. They should be included whether or not any output files (aside from standard output and error) are necessary.
Note that this example uses the Accounting Group "group_statistics_testjob" with the user's username appended at the end. If running a default, standard job, do not include this line. For more explanation, please see this page on [http://gryphn.phys.uconn.edu/statswiki/index.php/How_to_Submit_a_Job#Job_policy Job Policy].
The <i>universe</i> variable specifies the condor runtime environment. For the purposes of these independent jobs, the simplest "vanilla" universe suffices. In a more complicated parallel task, with checkpointing and migration, MPI calls etc., more advanced run-time environments are employed, often requiring specilized linking of the binaries. The lines specifying transfer settings are important to avoid any assumptions about accessibility over nfs. They should be included whether or not any output files (aside from standard output and error) are necessary.
=== Job Submission and Management ===
=== Job Submission and Management ===
While logged in on stats, the job is submitted with:
While logged in on stats, the job is submitted with:
universe = vanilla
universe = vanilla
Requirements = ParallelSchedulingGroup == "stats group"
Requirements = ParallelSchedulingGroup == "stats group"
+AccountingGroup = "group_statistics_testjob.username"
should_transfer_files = YES
should_transfer_files = YES
== Matlab example ==
== Matlab example ==
=== The Problem and Code ===
=== The Problem and Code ===
Matlab can be run in batch mode (i.e. non-interactive mode) on the cluster. No graphics can be used when running on the cluster. The following example demonstrates a simple Matlab example which saves the output to be opened later in Matlab interactively.
Matlab can be run in <b>batch mode (i.e. non-interactive mode)</b> on the cluster. <b>No graphics</b> can be used when running on the cluster. The following example demonstrates a simple Matlab example which saves the output to be opened later in Matlab interactively.
File: Matlab_example.m
File: Matlab_example.m
universe = vanilla
universe = vanilla
Requirements = ParallelSchedulingGroup == "stats group"
Requirements = ParallelSchedulingGroup == "stats group"
+AccountingGroup = "group_statistics_testjob.username"
initialdir = /path/to/your/jobs/directory
initialdir = /path/to/your/jobs/directory
transfer_input_files = Matlab_example.m, runMatlab
transfer_input_files = Matlab_example.m, runMatlab
By this time, only 6 jobs are left on the cluster, all with status 'R' - running. Various statistics are given including a job ID number. This handle is useful if intervention is required like manual removal of frozen job instances from the cluster. A command condor_rm 7.28 would remove just that instance, whereas condor_rm 7 will remove this entire job.
By this time, only 6 jobs are left on the cluster, all with status 'R' - running. Various statistics are given including a job ID number. This handle is useful if intervention is required like manual removal of frozen job instances from the cluster. A command condor_rm 7.28 would remove just that instance, whereas condor_rm 7 will remove this entire job.
== Acknowledgement ==
== Acknowledgement ==
Examples provided by Igor Senderovich, Alex Barnes, Yang Liu
Examples provided by Igor Senderovich, Alex Barnes, Yang Liu