Common DSRC Commands and Tools
BC Project: FY10-06
Date of Policy: 23 Mar 2011
Last Updated: 04 Nov 2021 (see Revision Log)
This policy brings together common commands and tools initiated and developed by the Baseline Configuration Team. The commands are available in the default PATH on all user-accessible systems at the participating HPCMP centers.
bcmodulecommand works with modules on the HPC systems. The command executes like the standard
modulecommand, but has numerous improvements and new features. Since
moduledoes, users can think of it as a total replacement, though technically it is a "wrapper" which calls
bcmodulecommand makes compiler and MPI modulefile names more consistent, finds modules, searches for strings in modulefiles, and makes output easier to read. The
bcmoduleadds new features to the module command but does not replace it. For more details, click on additional information.
- This command checks the status of HPCMP shared applications grouped into two distinct categories: Software License Buffer (SLB) applications and non-SLB applications. For more details, click on additional information.
- This command displays information about jobs in the batch queueing system. Fields displayed include job number and name, user name, subproject, cores/nodes requested, status, and queue, as well as several time settings. In addition, estimated job start time (when available) and relative job priority are displayed in the Waiting Jobs section. For more details, click on additional information.
- This command displays memory-use and load-average information for all login nodes of the system on which it is executed. Information on memory-use and load average may help users choose a specific node on which they wish to do their interactive work. For more details, click on additional information.
- The utility
qflagcollects information about the user and the user's jobs and sends a message about the reported problem without any need to leave the HPC system. For more details, click on additional information.
- This command prints a full report on a running or completed batch job with an option to include chronological log file entries for the job from the batch queueing system. The command can also list all completed jobs for a given user over a specified number of days in the past.
- This batch job monitoring command returns the standard output (STDOUT) and standard error (STDERR) messages for any submitted batch job from the start of execution until the job run is complete.
- This command displays various reports about jobs in the batch queuing system. Among the attributes that are displayed are: job number, user name, queue name, job name, cores requested, wall time requested and used, and job status. The command can also display the reason jobs are in a Queued state, the maximum wall time remaining for running jobs, and a "load percentage" based on cores requested versus cores available. Finally, the reports can be filtered according to queue name, user name, status, and job number. For more details, click on additional information.
- This command displays current batch queuing system information. Attributes included in the queuing information are: queue name, maximum wall time, maximum cores, jobs (running and pending), cores (running and pending) and queue running. The command also displays node usage information (cores available, cores running, and cores free). For more details, click on additional information.
- This command produces two reports on a user's file system quota and usage information. The default report
provides quota and usage information for the storage areas in which the user owns data
on the current system. The second report, produced by
show_storage -s, provides quota and usage information for the storage areas in which the user owns data on all systems at the local center. For more details, click on additional information.
- This command produces two reports on the allocation and utilization of a user's subprojects.
The default report provides this information for all subprojects of which the user is a
member on the current system. The second report, produced by
show_usage -s, provides it for all the user's subprojects on all systems at the local center.
The show_usage command is designed to be executed by individual users from the command line. The Centers may choose to execute the command on each user's behalf at login. However, the Centers are not required to display show_usage upon login. For more details, click on additional information.
All commands included in this policy will be made available in the user's default
$PATH on all HPCMP allocated machines.
|04 Nov 2021
|BC Team Audit - Added qhist command and made grammatical updates
|11 Jun 2019
|Added verbiage to the show_usage command
|11 Mar 2019
|Added qflag command
|21 Jun 2018
|BCT Team Audit - Added cqstat command and updated additional information pages
|16 Oct 2017
|18 Sep 2017
|07 Jul 2016
|BC Team Audit
|15 Apr 2014
|BC Team Audit
|25 Apr 2012
|BC Team Audit
|27 Sep 2011